Explore the vast range of titles available.

This paper presents the development of a new complete wearable system for detecting breast tumors based on fully textile antenna-based sensors. The proposed sensor is compact and fully made of textiles so that it fits conformably and comfortably on the breasts with dimensions of 24 × 45 × 0.17 mm3 on a cotton substrate. The proposed antenna sensor is fed with a coplanar waveguide feed for easy integration with other systems. It realizes impedance bandwidth from 1.6 GHz up to 10 GHz at |S11| ≤ −6 dB (VSWR ≤ 3) and from 1.8 to 2.4 GHz and from 4 up to 10 GHz at |S11| ≤ −10 dB (VSWR ≤ 2). The proposed sensor acquires a low specific absorption rate (SAR) of 0.55 W/kg and 0.25 W/kg at 1g and 10 g, respectively, at 25 dBm power level over the operating band. Furthermore, the proposed system utilizes machine-learning algorithms (MLA) to differentiate between malignant tumor and benign breast tissues. Simulation examples have been recorded to verify and validate machine-learning algorithms in detecting tumors at different sizes of 10 mm and 20 mm, respectively. The classification accuracy reached 100% on the tested dataset when considering |S21| parameter features. The proposed system is vision as a “Smart Bra” that is capable of providing an easy interface for women who require continuous breast monitoring in the comfort of their homes.

Rapid urbanization has caused severe deterioration of air quality globally, leading to increased hospitalization and premature deaths. Therefore, accurate prediction of air quality is crucial for mitigation planning to support urban sustainability and resilience. Although some studies have predicted air pollutants such as particulate matter (PM) using machine learning algorithms (MLAs), there is a paucity of studies on spatial hazard assessment with respect to the air quality index (AQI). Incorporating PM in AQI studies is crucial because of its easily inhalable micro-size which has adverse impacts on ecology, environment, and human health. Accurate and timely prediction of the air quality index can ensure adequate intervention to aid air quality management. Therefore, this study undertakes a spatial hazard assessment of the air quality index using particulate matter with a diameter of 10 μm or lesser (PM10) in Selangor, Malaysia, by developing four machine learning models: eXtreme Gradient Boosting (XGBoost), random forest (RF), K-nearest neighbour (KNN), and Naive Bayes (NB). Spatially processed data such as NDVI, SAVI, BU, LST, Ws, slope, elevation, and road density was used for the modelling. The model was trained with 70% of the dataset, while 30% was used for cross-validation. Results showed that XGBoost has the highest overall accuracy and precision of 0.989 and 0.995, followed by random forest (0.989, 0.993), K-nearest neighbour (0.987, 0.984), and Naive Bayes (0.917, 0.922), respectively. The spatial air quality maps were generated by integrating the geographical information system (GIS) with the four MLAs, which correlated with Malaysia’s air pollution index. The maps indicate that air quality in Selangor is satisfactory and posed no threats to health. Nevertheless, the two algorithms with the best performance (XGBoost and RF) indicate that a high percentage of the air quality is moderate. The study concludes that successful air pollution management policies such as green infrastructure practice, improvement of energy efficiency, and restrictions on heavy-duty vehicles can be adopted in Selangor and other Southeast Asian cities to prevent deterioration of air quality in the future. Graphical abstract

This paper proposes a methodology for correlating products derived by Synthetic Aperture Radar (SAR) measurements and laser profilometric road roughness surveys. The procedure stems from two previous studies, in which several Machine Learning Algorithms (MLAs) have been calibrated for predicting the average vertical displacement (in terms of mm/year) of road pavements as a result of exogenous phenomena occurrence, such as subsidence. Such algorithms are based on surveys performed with Persistent Scatterer Interferometric SAR (PS-InSAR) over an area of 964 km2 in the Tuscany Region, Central Italy. Starting from this basis, in this paper, we propose to integrate the information provided by these MLAs with 10 km of in situ profilometric measurements of the pavement surface roughness and relative calculation of the International Roughness Index (IRI). Accordingly, the aim is to appreciate whether and to what extent there is an association between displacements estimated by MLAs and IRI values. If a dependence exists, we may argue that road regularity is driven by exogenous phenomena and MLAs allow for the replacement of in situ surveys, saving considerable time and money. In this research framework, results reveal that there are several road sections that manifest a clear association among these two methods, while others denote that the relationship is weaker, and in situ activities cannot be bypassed to evaluate the real pavement conditions. We could wrap up that, in these stretches, the road regularity is driven by endogenous factors which MLAs did not integrate during their training. Once additional MLAs conditioned by endogenous factors have been developed (such as traffic flow, the structure of the pavement layers, and material characteristics), practitioners should be able to estimate the quality of pavement over extensive and complex road networks quickly, automatically, and with relatively low costs.

Predicting and accurately identifying heart disease is a significant challenge in the field of medicine, and the problem of cardiovascular disease predetermine in the health care system is regarded as an essential challenge. Patients have access to more expensive surgical procedures at these rapidly expanding health care organisations. Recent years have seen an increase in the prevalence of heart disease; this means that despite the progress that has been made in medicine, the prevalence of cardiovascular disease continues to rise at an alarming rate. The primary contributors to the development of these illnesses are a sedentary lifestyle, excessive use of alcohol, insufficient time spent being physically active, and the use of cigarette products. As a result, there is a requirement for a cloud-based framework (CBF) that is capable of monitoring health information and making accurate predictions regarding it. Recently, techniques from the field of machine learning have been applied in an effort to address issues of this nature. But the method that is being suggested uses a cloud-based and cloud-based four-step process to improve surveillance of patients’ health information. This is done to improve the process of forecasting patients’ health information. Detecting and categorising cardiac illness can be accomplished through the application of two distinct kinds of machine learning techniques. After that, an analysis is performed to determine how accurate those techniques are. In order to assess how effectively they work, evaluation parameters are utilised.

The importance of power quality monitoring, detection, and classification on electrical systems increased recently in terms of economics, security, the efficiency depending on the spreading of the smart grid. The current monitoring systems are based on IEEE 1159 and similar standards under some stable conditions and assuming. But the detailed measurements of power quality disturbances should be evaluated robustly even in a noisy environment with a specific method for each power quality disturbance (PQD) for every window. Because this approach is very time-consuming and not feasible, most studies with different techniques promote primarily detection of the PQDs and then classifications of these. For this purpose, a study using hyperparameter optimization of machine learning algorithms (MLAs) is executed for the detection and classification (D&C) of PQDs. 21 class datasets consisting of single and multiple PQDs with different-level noise are prepared randomly. These datasets are trained and tested with a lot of MLAs in a workstation as the time-series signals with no preprocessing apart from the other methods. The results obtained from comparative MLAs show that the best MLA and the hyperparameters of that are kNN, RF, LightGBM, and XGBoost with an accuracy of 99.82%, 98.78%, 98.10%, and 94.77%, respectively. In as much as the optimized parameters and the related MLAs were obtained by investigating the time-series signal datasets with no preprocessing in the whole hyperparameter space, this approach brings the advantages of high accuracy.

In the HOMAGE (Heart Omics in AGEing) trial, spironolactone reduced serum concentrations of procollagen Type I C‐terminal propeptide (PICP), a fibrosis biomarker, in patients at risk of heart failure. To elucidate the underlying mechanisms, multidimensional analyses including proteomics were conducted. Olink cardiovascular and inflammation panels (n = 276 proteins) were measured in plasma from 488 HOMAGE participants at baseline, 1 month, and 9 months after randomization. Proteins associated with PICP changes were identified using machine learning algorithms (MLAs). Selected candidates were further analyzed in patients with heart failure and preserved ejection fraction (Aldo‐DHF trial). Linear regression and mediation analyses assessed which MLA‐selected proteins mediated spironolactone's effects on PICP. MLAs consistently linked PICP reduction to changes in biomarkers of collagen (e.g., decreased COL1A1), fatty acid metabolism (e.g., increased FABP4), immune function (e.g., increased CCL24 and IL6RA, and decreased FLT3L), neurological function (e.g., increased DNER), cell–matrix interactions (e.g., increased galectin‐9 [GAL9] and decreased thrombospondin‐2 [THBS2]), and reduced NT‐proBNP. Mediation analysis suggested that changes in GAL9 and THBS2 were associated with spironolactone‐induced PICP reduction, which was confirmed in Aldo‐DHF patients. This study raises the hypothesis that spironolactone inhibits collagen synthesis via inflammatory, metabolic, and extracellular matrix pathways, and particularly through modulation of GAL9 and THBS2. In HOMAGE, 276 plasma proteins were profiled using Olink panels. Machine learning algorithms identified galectin‐9 (GAL9), thrombospondin‐2 (THBS2), and NT‐proBNP as predictors of changes in procollagen type I C‐terminal propeptide (PICP) after spironolactone treatment. Decreasing THBS2 and increasing GAL9 were associated with PICP reduction in HOMAGE and Aldo‐DHF patients, suggesting a potential mediating role of these proteins in fibrosis modulation .

IoT is essential in today's surveillance environment for maintaining safety and providing the best fire detection performance. Cameras are being installed in a lot of places because fire can seriously damage both residential and commercial sectors. However, the installed video monitoring device may generate data or perspectives that are odd or skewed. In view of these shortcomings, a convolutional neural network-based approach is proposed. The data set for testing the model is provided by an integrated sensor system that was built using an ESP-32 CAM image sensor, a number of complementing sensors, and an Arduino Uno microcontroller. Using drop out techniques, the model also solves the issue of overfitting in the paper. The performance of our approach was compared to that of other transfer learning models, such as MobileNet, Resnet50 and VGG19 that uses well-known state-of-the-art architectures. The main goal of this paper is to build a model which gives high accuracy while consuming low computational power during inference. The proposed model accuracy relative to latency is better than the transfer learning models. Furthermore, the approach is to build a well-generalised model for unknown data, resulting in efficient generalisation and fewer false predictions.

Every day, huge amounts of video are created and stored, yet many of these are inappropriate for deep learning or other automation-related tasks due to being noisy and poor quality. Although digital video processing has many uses, little research or software is produced. Until recently, video denoising with neural networks was a relatively unexplored field. FastRWDnet, the solution we present in this research, achieves comparable results to existing state-of-the-art FastDVDnet approach while requiring much less processing time. In comparison with other existing neural network denoisers, our technique has several advantageous qualities, including short run-times and the ability to handle a wide variety of noise levels with a single network model. In order to achieve faster segmentation, the novel technique of FastRWDnet uses modified bottleneck blocks of ENet for denoising purposes instead of UNet, which was employed in the FastDVDnet. Due to the architecture’s qualities, it is possible to run this algorithm in a real-time implementation. It is suitable for practical denoising applications due to its combination of high denoising performance and minimal computational load. We have implemented our algorithm on a web architecture and successfully obtained real-time denoising output for both prerecorded video footage and real-time video streams.

Recent diagnostic observations have raised concerns regarding malignancy issues in untreated skin cancer. Over the last two decades, dermoscopy has led to non-invasive clinical diagnosis of cancer types, typically Melanoma, Basal Cell Carcinoma (BCC), and Squamous Cell Carcinoma (SCC). Raising concerns coupled with clinical (image) data motivated this study which focuses on a Machine Learning (ML) based approach to properly classify the skin cancer into one of the three types mentioned earlier. In this regard, the study also uses a unique image pre-processing network which cleans and processes the images prior to injection into the ML models. In this study, the image pre-processing network primarily comprises of Gaussian noise removal, blackhat operation, and Otsu segmentation. Post processing, a novel Hybrid Color Features (HCF) algorithm has been used for feature extraction in terms of texture, shape and color features. Outlier handling was done using the z-score rescaling approach. In comparison to the traditional ML approach, it had been observed that the novel soft voting ensemble classifier (SVEC) exhibited better results. The SVEC along with boosting fetched an accuracy of 95.5%, 96.3%, and 96.7% for Melanoma, BCC, and SCC skin cancers, respectively. Peer comparison with prior ML initiatives further confirmed the novelty of the SVEC approach.

Deploying a web of CCTV cameras for surveillance has become an integral part of any smart city’s security procedure. This, however, has led to a steady increase in the number of cameras being deployed. These cameras generate a large amount of data, which needs to be further analyzed. Our next step is to achieve a network of cameras spread across a city that does not require any human assistance to detect, recognize and track a person. This paper incorporates various algorithmic techniques used in order to make surveillance systems and their use cases so as to enable less human intervention dependent as much as possible. Even though many of these methods do carry out the task graciously, there are still quite a few obstructions such as computational resources required for model building, training time for the models, and many more issues that hinder the process and hence, constrain the possibility of easy implementation. In this paper, we also intend to shift the paradigm by providing evidence toward the use of technologies like Fog computing and edge computing coupled with the surveillance technology trends, which can help to achieve the goal in a sustainable manner with lesser overheads.