Two-Stage Motion Artifact Reduction Algorithm for rPPG Signals Obtained from Facial Video Recordings.

Recent years have witnessed the publication of many research articles regarding the contactless measurement and monitoring of heart rate signals deduced from facial video recordings. The techniques presented in these articles, such as examining the changes in the heart rate of an infant, provide a noninvasive assessment in many cases where the direct placement of any hardware equipment is undesirable. However, performing accurate measurements in cases that include noise motion artifacts still presents an obstacle to overcome. In this research article, a two-stage method for noise reduction in facial video recording is proposed. The first stage of the system consists of dividing each (30) seconds of the acquired signal into (60) partitions and then shifting each partition to the mean level before recombining them to form the estimated heart rate signal. The second stage utilizes the wavelet transform for denoising the signal obtained from the first stage. The denoised signal is compared to a reference signal acquired from a pulse oximeter, resulting in the mean bias error (0.13), root mean square error (3.41) and correlation coefficient (0.97). The proposed algorithm is applied to (33) individuals being subjected to a normal webcam for acquiring their video recording, which can easily be performed at homes, hospitals, or any other environment. Finally, it is worth noting that this noninvasive remote technique is useful for acquiring the heart signal while preserving social distancing, which is a desirable feature in the current period of COVID-19.

Twinned Residual Auto-Encoder (TRAE)-A new DL architecture for denoising super-resolution and task-aware feature learning from COVID-19 CT images.

The detection of the COronaVIrus Disease 2019 (COVID-19) from Computed Tomography (CT) scans has become a very important task in modern medical diagnosis. Unfortunately, typical resolutions of state-of-the-art CT scans are still not adequate for reliable and accurate automatic detection of COVID-19 disease. Motivated by this consideration, in this paper, we propose a novel architecture that jointly affords the Single-Image Super-Resolution (SISR) and the reliable classification problems from Low Resolution (LR) and noisy CT scans. Specifically, the proposed architecture is based on a couple of Twinned Residual Auto-Encoders (TRAE), which exploits the feature vectors and the SR images recovered by a Master AE for performing transfer learning and then improves the training of a "twinned" Follower AE. In addition, we also develop a Task-Aware (TA) version of the basic TRAE architecture, namely the TA-TRAE, which further utilizes the set of feature vectors generated by the Follower AE for the joint training of an additional auxiliary classifier, so to perform automated medical diagnosis on the basis of the available LR input images without human support. Experimental results and comparisons with a number of state-of-the-art CNN/GAN/CycleGAN benchmark SISR architectures, performed by considering × 2 , × 4 , and × 8 super-resolution (i.e., upscaling) factors, support the effectiveness of the proposed TRAE/TA-TRAE architectures. In particular, the detection accuracy attained by the proposed architectures outperforms the corresponding ones of the implemented CNN, GAN and CycleGAN baselines up to 9.0%, 6.5%, and 6.0% at upscaling factors as high as × 8 .

An Effective COVID-19 CT Image Denoising Method Based on a Deep Convolutional Neural Network

Background: Faced with the global threat posed by SARS-CoV-2 (COVID-19), low-dose computed tomography (LDCT), as the primary diagnostic tool, is often accompanied by high levels of noise. This can easily interfere with the radiologist's assessment. Convolutional neural networks (CNN), as a method of deep learning, have been shown to have excellent effects in image denoising. Objective: The objective of the study was to use modified convolutional neural network algorithm to train the denoising model. The purpose was to make the model extract the highlighted features of the lesion region better and ensure its effectiveness in removing noise from COVID-19 lung CT images, preserving more important detail information of the images and reducing the adverse effects of denoising. Methods: We propose a CNN-based deformable convolutional denoising neural network (DCDNet). By combining deformable convolution methods with residual learning on the basis of CNN structure, more image detail features are retained in CT image denoising. Results: According to the noise reduction evaluation index of PSNR, SSIM and RMSE, DCDNet shows excellent denoising performance for COVID-19 CT images. From the visual effect of denoising, DCDNet can effectively remove image noise and preserve more detailed features of lung lesions. Conclusion: The experimental results indicate that the DCDNet-trained model is more suitable for image denoising of COVID-19 than traditional image denoising algorithms under the same training set. © 2023 Bentham Science Publishers.

JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution

With the growing importance of preventing the COVID-19 virus in cyber-manufacturing security, face images obtained in most video surveillance scenarios are usually low resolution together with mask occlusion. However, most of the previous face super-resolution solutions can not efficiently handle both tasks in one model. In this work, we consider both tasks simultaneously and construct an efficient joint learning network, called JDSR-GAN, for masked face super-resolution tasks. Given a low-quality face image with mask as input, the role of the generator composed of a denoising module and super-resolution module is to acquire a high-quality high-resolution face image. The discriminator utilizes some carefully designed loss functions to ensure the quality of the recovered face images. Moreover, we incorporate the identity information and attention mechanism into our network for feasible correlated feature expression and informative feature learning. By jointly performing denoising and face super-resolution, the two tasks can complement each other and attain promising performance. Extensive qualitative and quantitative results show the superiority of our proposed JDSR-GAN over some competitive methods. IEEE

NOISE POLLUTION AND ARTERIAL HYPERTENSION

Environmental noise significantly impacts human health and well-being. It is a widespread problem in Europe, where at least one in five people are exposed to harmful levels of noise. Hearing loss is the most known health effect related to noise exposure. There is, however, growing data that links noise exposure to hypertension, coronary artery disease, and stroke. According to some theories, this relationship may be explained by the indirect pathway of noise exposure, which can cause sympathetic and endocrine activation, as well as several cognitive and emotional responses, including annoyance. Noise exposure leads to stress reactions independent of cognitive involvement. There is a possibility that noise exerts its effects directly through synaptic interactions, as well as through cognitive and emotional effects. Epidemiological studies indicate that nocturnal noise exposure has more profound health consequences. Nighttime noise exposure is associated with an increase in heart rate due to sympathetic activation or parasympathetic withdrawal, and with an increase in blood pressure as well as endothelial dysfunction. Hypertension is a common condition and is an important risk indicator for other cardiovascular diseases. Previous studies showed an association between noise exposure, blood pressure and arterial hypertension. Meta-analysis of cross-sectional studies found an increase of hypertension prevalence per 10 dB increase in daytime average road traffic noise level. There is, however, some heterogeneity among these studies. Prospective studies have also found an association between aircraft noise exposure and hypertension, supporting the cross-sectional findings. The analyses, of data from the large Hypertension and Exposure to Noise near Airports (HYENA) study, showed that an increase in nocturnal aircraft noise exposure per 10 dB was associated with an increased incidence of hypertension. The meaningful effect of night-time aircraft noise on arterial hypertension was also observed in the prospective observation of the subset of individuals from that study. In a longitudinal observation of 420 participants, higher aircraft noise exposure during the night significantly associated with the incidence of hypertension. Previous cross-sectional case-control study conducted in 2015, in 2 suburban areas of Krakow, Poland, revealed an increase in blood pressure and arterial stiffness as determined by carotid - femoral pulse wave velocity in individuals exposed to increased aircraft noise levels. However, even short-term noise reduction, as experienced during the COVID-19 lockdown, may reverse those unfavorable effects. As a result of these observations, noise mitigation strategies are important for cardiovascular health.

Retrospective analysis of individualised melatonin regimens and a multidisciplinary targeted approach in managing insomnia during the second wave of COVID-19

Introduction: The therapeutic benefits of sleep in the critically ill has been extensively studied in the medical literature.1 Chronic insomnia increases a patient's risk of delirium, cortical atrophy, diabetes, cancer, cardiovascular death from arterial hypertension, myocardial infarction and heart failure.2 Insomnia reduces interaction during videocalls with family and limits co-operation with physiotherapy, medical and nursing interventions, potentially delaying rehabilitation and recovery. Objectives: To improve sleep by introducing an individualised melatonin regimen and a multidisciplinary targeted approach to managing insomnia in an adult intensive care unit. Methods: A retrospective analysis was conducted in a single centre UK adult ICU. Data was retrieved from pharmacy dispensing records, electronic medical notes and prescriptions from September 2020 to March 2021. The primary outcome was resolution of insomnia. Other information collected included causes of insomnia, referral to psychology for cognitive behavioural therapy (CBT), prevalence and resolution of delirium, adverse effects, and death. Each patient received a tailor made regimen based on Bellapart et al's original concept of mimicking the natural endogenous secretion of melatonin.3 However, unlike previous studies3,4,5 dosing was modified and adjusted according to patient response. A loading dose of 0.75 to 3mg was administered at 21:00 followed by a smaller hourly dose of 0.25 to 0.5mg between 22:00 and 03:00. Additionally, the duration of treatment continued for as long as therapeutic benefit was realised, which included post discharge from ICU. Prior experience of conventional melatonin dosing did not demonstrate therapeutic benefit from the original pilot study and when nursing staff inadvertently omitted the hourly dose between 10pm and 3am. Adverse effects were documented. Sleep hygiene measures were introduced and standardised where possible e.g. ear plugs, eye mask, dim lights, environmental noise reduction and minimal night time physical interventions from nursing and medical staff. The principal investigator referred to psychology patients who expressed fear and anxiety as a cause of insomnia. Results: 132 patients were admitted during September 2020 to March 2021. 30 patients received tailor made melatonin regimens (22.7%). The medical notes of four (13.3%) patients could not be accessed for data collection and were, therefore, excluded from the study. The primary outcome of resolution of insomnia occurred in 23 out of 26 (88.4%) patients. At the time of ICU discharge, delirium had occurred in 15 patients (57.7%), resolved in 10 patients (66.7%), three (20%) patients remained intermittently delirious, one remained continuously delirious, and one died. Mechanical ventilation, environmental noise, necessary medical and nursing interventions throughout the night and infection accounted for 23 (88.4%) of patients' insomnia. Fear or anxiety were expressed by eight (30.8%) patients as a cause of insomnia whilst medicines e.g. steroids, beta blockers accounted for six patients (26.1%). Seven patients (26.9%) expressing fear or anxiety were referred to psychology for adjunctive CBT. One patient experienced excessive daytime drowsiness, which resolved with dose regimen adjustment. One patient died of a cause unrelated to melatonin. Conclusion: An individualised melatonin regimen combined with a multidisciplinary targeted approach can result in resolution of insomnia in ICU patients, with minimal risk of adverse effects.

Contrast Enhancement and Noise Reduction of chest X-ray images

X-ray radiography is used to get medical images of body parts such as chest, bones etc. These images help in detection of anomaly in inspected body part, for eg- Chest X-ray are used for detection of many diseases such as Covid-19, Pneumonia and Cancer. However, images obtained from radiography are low in contrast and with high noise level. Enhancement of an image is very crucial for the diagnostic purpose, as currently medical images are very helpful in identifying various disease and problem in human body. With the technical support, the enhancement is considered one of the first-rate methods for the betterment of visualization and raising the standard for understanding and clearing the image details. In our work, we have focused on the contrast enhancement and noise reduction, using Histogram equalization, CLAHE (Contrast Limited Adaptive Histogram Equalization), median filter and DCT filter for chest X-ray images of COVID-19 positive patients. The dataset of 6,334 images are collected from the Kaggle repository. All these methods are combined and as a result, has provided the best output by giving a colored enhanced image, highlighting the major details. This work will be helpful in the diagnosis of various kind of the diseases from radiographic approach. In the future, we will extend the process for the diagnostic part of COVID-19 from the enhanced images dataset, which will help in easy detection and work as a technological support to healthcare system. © 2022 IEEE.

Comparative Analysis of Image Enhancement Techniques for Chest X-ray Images

X-ray radiography plays a crucial part in diagnosis of various diseases in human body like Covid-19, Cancer and Pneumonia. The images obtained through X-ray radiography is interpreted by Surgeons, Pathologists and Radiologists for detecting anomaly in scanned body part. Chest X-ray is one of the cheapest and easily accessible tests of functioning of chest and lungs. However, images obtained through X-ray are not very clear, low in contrast and with lesser variation in gray level. Image enhancement is done for better visualization of images and bringing forward the underlying details of image. The Kaggle repository of total 6334 chest X-ray images were used for experimentation and calculation works. In this paper, we have compared various combinations of contrast enhancement techniques such as CLAHE, Morphological operations (black and white hat transforms) and noise reduction techniques like Median filter, DCT and DWT. The Comparison was done on the basis of image quality assessment parameters such as MSE, PSNR, and AMBE. The results showed that fusion of CLAHE and DWT techniques gave best results with highest PSNR value and lowest AMBE among the various models discussed. The proposed methodology shall be very helpful in diagnosis of diseases from chest X-ray images. © 2022 IEEE.

Multitemporal Scenic Evaluation of Urban Coastal Sites: A Peruvian Case Study

Along the coast of Peru, intensive urbanization and tourism development were related to coastal scenery deterioration. This investigation carried out a scenery evaluation of 20 urban beaches from the “Circuito de Playas de la Costa Verde” (CPCV), a key beach corridor in Lima (Peru). For this purpose, the Coastal Scenic Evaluation System (CSES) was applied in three different seasons, using fuzzy logic to reduce observer subjectivity and estimate the Evaluation index (D). A total of 26 parameters were evaluated to estimate the D value during summer 2020, winter 2020, and summer 2021, to determine the temporal variability of the landscape of an urban coastal sector, such as the CPCV. The results show that all evaluated beaches are classified as very unattractive sites (Class V). Additionally, no significant differences were found between seasons but between beaches. Litter and disturbance factors (noise) were the main human parameters that had low and variable scores during assessments and influenced the D index value estimate. This scenery assessment proposes further implementations of new beach management strategies and actions focusing on landscaping and conserving coastal ecosystems. Strengthening monitoring to reduce noise and litter disturbance and promoting environmentally friendly coastal usage are vital aspects that must be implemented.

The IMU augment SLAM on Unmanned Vehicle for detection of protective measures in COVID-19

Detecting protective measures (e.g., masks, goggles and protective clothing) is a momentous step in the fight against COVID-19. The detection mode of unmanned devices based on Simultaneous localization and mapping (SLAM) and fusion technology is more efficient, economical and safe than the traditional manual detection. In this paper, a tightly-coupled nonlinear optimization approach is used to augment the visual feature extraction of SLAM by the gyroscope of the IMU to obtain a high-precision visual inertial system for joint position and pose estimation. Based on the VINS-Mono frame, first, an LSD algorithm based on a conditional selection strategy is proposed to extract line features efficiently. Then, we propose recovering missing point features from line features. Moreover, we propose a strategy to recover vanishing point features from line features, and add residuals to the SLAM cost function based on optimization, which optimizes point-line features in real time to promote the tracking and matching accuracy. Second, the wavelet threshold denoising method based on the 3σcriterion is used to carry out real-time online denoising for gyroscope to improve the output precision. Our WD-PL-VINS was measured on publicly available EuRoC datasets, TUM VI datasets and evaluated and validated in lab testing with a unmanned vehicle (UV) based on the NVIDIA Jetson-TX2 development board. The results show that our method’s APE and RPE on MH 03 easy sequences are improved by 69.28% and 97.66%, respectively, compared with VINS-Mono. IEEE

A new approach for reduction of the noise from microscopy images using Fourier decomposition

In this paper, an efficient method based on the Fourier decomposition method (FDM) is presented for noise removal of medical microscopic images. We propose an adaptive thresholding technique based FDM for denoising of heavily degraded images. An accurate image deconvolution is done with variance stabilization transformation and multi-scale Wiener filtering as a pre-processing step. The different series of frequency intrinsic band functions (FIBF's) obtained with FDM which are further separated into noise and signal-significant FIBF's based on cosine similarity index. The FDM adaptive thresholding technique is used to filter-out the unwanted frequency coefficients related to mixed Poisson-Gaussian noise (MPG). The thresholded FIBF's and signal significant FIBF's are combined to obtained reconstructed output. Finally, the optimization is done using mixed noise unbiased risk estimate (MNURE). To evaluate the effectiveness of proposed scheme, we have compared the results of the proposed scheme with six different state-of-the-art techniques. The simulation results verify, the effectiveness of proposed method. The proposed algorithm achieves better performance in terms of four quantitative evaluation measures by reducing the effect of noise.

The dynamics of the first wave of COVID-19 on environment and wildlife– a boon or a bane?

Even though COVID-19 has drastically weighed upon the humankind, still there is a "silver lining" to see in this dark time. Amidst of this pandemic, most of the human activities were restricted to break the chain of infection which resulted the remarkable change in nature. It has been reported that due to halt in air travel, reduction in the use of fossil fuels, way less functioning of vehicles, shutdown of industries has complied the change in air pollution levels and also change in river water quality. Reports also showed the reduction in particulate matter (PM 2.5 and PM 10), greenhouse gases emissions, massive improvement in the Air quality index (AQI), reduction in the NOX and SOX's levelhas clearly stipulated that nature has got it's time to "revive". Even the global carbon emission has reported to reduced reluctantly which is expected to be the biggest such drop since World War II. Despite conducting water-cleansing projects and spending a lot of money, the situation of the water bodies were far better now during first lockdown. Moreover, migration and breeding of the birds and animals have been reported to be restored to normal pattern due to depletion in man-animal conflict. Apart from the positive, negative impacts on the nature are also being experienced. Our review work is highlighting such impacts witnessed during the first wave of COVID-19, like, the significant improvement in air and water quality, reduction in environmental noise, therefore an in turn cleaner and quieter habitat for the wildlife to mate and also to quench their curiosities by their surprising excursions;but there are also some negative aspects as well, like reduction in recycling and the increase in waste, increased poaching and even lone shuttering of zoo animals.

Urbanization effect on Hyderabad seismic station

Seismographs record earthquakes and also record various types of noise, including anthropogenic noise. In the present study, we analyse the influence of the lockdown due to COVID-19 on the ground motion at CSIR-NGRI HYB Seismological Observatory, Hyderabad. We analyse the noise recorded a week before and after the implementation of lockdown by estimating the probability density function of seismic power spectral density and by constructing the daily spectrograms. We find that at low frequency (<1 Hz), where the noise is typically dominated by naturally occurring microseismic noise, a reduction of ~2 dB for secondary microseisms (7–3 s) and at higher frequency (1–10 Hz) a reduction of ~6 dB was observed during the lockdown period. The reduction in higher frequencies corresponding to anthropogenic noise sources led to improving the SNR (signal-to-noise ratio) by a factor of 2 which is the frequency bandwidth of the microearthquakes leading to the identification of microearthquakes with Ml around 3 from epicentral distances of 180 km.

Transport Systems for Sustainability: Policy, Planning and Exploitation

There are several SDG targets directly linked to transport, including SDG 3 on health (increased road safety), SDG 7 on energy, SDG 8 on decent work and economic growth, SDG 9 on resilient infrastructure, SDG 11 on sustainable cities (access to transport and expanded public transport), SDG 12 on sustainable consumption and production (ending fossil fuel subsidies) and SDG 14 on oceans, seas and marine resources. The authors concluded that the construction of the new artery by the city centre, using appropriate technical solutions and traffic organization (tunnel, noise barriers, roundabouts, speed limit) likely contributed to an overall reduction in NO2 concentrations. Tsakalidis, Gkoumas, Grosso and Pekár present an overview of TRIMIS and its benefits as an integrated analytical tool that provides support to sustainable transport governance and decision-making. [...]it provides insights on current technology trends in the road transport domain with a focus on smart innovation and identifies emerging trends with a potential future impact through a dedicated case study, combining a techno-economic assessment with findings of a horizon scanning exercise. [...]we have four papers that focus on specific modes of transport—road and maritime:

KL-MOB: automated COVID-19 recognition using a novel approach based on image enhancement and a modified MobileNet CNN.

The emergence of the novel coronavirus pneumonia (COVID-19) pandemic at the end of 2019 led to worldwide chaos. However, the world breathed a sigh of relief when a few countries announced the development of a vaccine and gradually began to distribute it. Nevertheless, the emergence of another wave of this pandemic returned us to the starting point. At present, early detection of infected people is the paramount concern of both specialists and health researchers. This paper proposes a method to detect infected patients through chest x-ray images by using the large dataset available online for COVID-19 (COVIDx), which consists of 2128 X-ray images of COVID-19 cases, 8,066 normal cases, and 5,575 cases of pneumonia. A hybrid algorithm is applied to improve image quality before undertaking neural network training. This algorithm combines two different noise-reduction filters in the image, followed by a contrast enhancement algorithm. To detect COVID-19, we propose a novel convolution neural network (CNN) architecture called KL-MOB (COVID-19 detection network based on the MobileNet structure). The performance of KL-MOB is boosted by adding the Kullback-Leibler (KL) divergence loss function when trained from scratch. The KL divergence loss function is adopted for content-based image retrieval and fine-grained classification to improve the quality of image representation. The results are impressive: the overall benchmark accuracy, sensitivity, specificity, and precision are 98.7%, 98.32%, 98.82% and 98.37%, respectively. These promising results should help other researchers develop innovative methods to aid specialists. The tremendous potential of the method proposed herein can also be used to detect COVID-19 quickly and safely in patients throughout the world.

Noninvasive mechanical ventilation in the COVID-19 era: Proposal for a continuous positive airway pressure closed-loop circuit minimizing air contamination, oxygen consumption, and noise.

Noninvasive continuous positive airway pressure (NIV-CPAP) is effective in patients with hypoxemic respiratory failure. Building evidence during the COVID-19 emergency reported that around 50% of patients in Italy treated with NIV-CPAP avoided the need for invasive mechanical ventilation. Standard NIV-CPAP systems operate at high gas flow rates responsible for noise generation and inadequate humidification. Furthermore, open-configuration systems require a high concentration of oxygen to deliver the desired FiO2 . Concerns outlined the risk for aerosolization in the ambient air and the possible pressure drop in hospital supply pipes. A new NIV-CPAP system is proposed that includes automatic control of patient respiratory parameters. The system operates as a closed-loop breathing circuit that can be assembled, combining a sleep apnea machine with existing commercially available components. Analytical simulation of a breathing patient and simulation with a healthy volunteer at different FiO2 were performed. Inspired and expired oxygen fraction and inspired and expired carbon dioxide pressure were recorded at different CPAP levels with different oxygen delivery. Among the main findings, we report (a) a significant (up to 30-fold) reduction in oxygen feeding compared to standard open high flow NIV-CPAP systems, to assure the same FiO2 levels, and (b) a negligible production of the noise generated in ventilatory systems, and consequent minimization of patients' discomfort. The proposed NIV-CPAP circuit, reshaped in closed-loop configuration with the blower outside of the circuit, has the advantages of minimizing aerosol generation, environmental contamination, oxygen consumption, and noise to the patient. The system is easily adaptable and can be implemented using standard CPAP components.