Machine learning empowered COVID-19 patient monitoring using non-contact sensing:An extensive review

The severe acute respiratory syndrome coronavirus 2(SARS-CoV-2),which caused the coronavirus disease 2019(COVID-19)pandemic,has affected more than 400 million people worldwide.With the recent rise of new Delta and Omicron variants,the efficacy of the vaccines has become an important question.The goal of various studies has been to limit the spread of the virus by utilizing wireless sensing technologies to prevent human-to-human interactions,particularly for healthcare workers.In this paper,we discuss the current literature on invasive/contact and non-invasive/noncontact technologies(including Wi-Fi,radar,and software-defined radio)that have been effectively used to detect,diagnose,and monitor human activities and COVID-19 related symptoms,such as irregular respiration.In addition,we focused on cutting-edge machine learning algorithms(such as generative adversarial networks,random forest,multilayer perceptron,support vector machine,extremely randomized trees,and k-nearest neighbors)and their essential role in intelligent healthcare systems.Furthermore,this study highlights the limitations related to non-invasive techniques and prospective research directions.

Temperature trends and elevation dependent warming during 1965-2014 in headwaters of Yangtze River, Qinghai Tibetan Plateau

The understanding of temperature trends in high elevation mountain areas is an integral part of climate change research and it is critical for assessing the impacts of climate change on water resources including glacier melt, degradation of soils, and active layer thickness. In this study, climate changes were analyzed based on trends in air temperature variables(Tmax, Tmin, Tmean), and Diurnal Temperature Range(DTR) as well as elevation-dependent warming at annual and seasonal scales in the Headwaters of Yangtze River(HWYZ), Qinghai Tibetan Plateau. The Base Period(1965-2014) was split into two subperiods;Period-Ⅰ(1965-1989) and Period-Ⅱ(1990-2014) and the analysis was constrained over two subbasins;Zhimenda and Tuotuohe. Increasing trends were found in absolute changes in temperature variables during Period-Ⅱ as compared to Period-Ⅰ.Tmax, Tmin, and Tmean had significant increasing trends for both sub-basins. The highest significant trends in annual time scale were observed in Tmin(1.15℃ decade-1) in Tuotuohe and 0.98℃ decade-1 in Zhimenda sub-basins. In Period-Ⅱ, only the winter season had the highest magnitudes of Tmax and Tmin0.58℃ decade-1 and 1.26℃ decade-1 in Tuotuohe subbasin, respectively. Elevation dependent warming analysis revealed that Tmax, Tmin and Tmean trend magnitudes increase with the increase of elevations in the middle reaches(4000 m to 4400 m) of the HWYZ during Period-Ⅱ annually. The increasing trend magnitude during Period-Ⅱ, for Tmax, is 1.77, 0.92, and 1.31℃ decade-1, for Tmin 1.20, 1.32 and 1.59℃ decade-1,for Tmean 1.51, 1.10 and 1.51℃ decade-1 at elevations of4066 m, 4175 m and 4415 m respectively in the winter season. Tmean increases during the spring season for> 3681 m elevations during Period-Ⅱ, with no particular relation with elevation dependency for other variables. During the summer season in Period Ⅱ, Tmax, Tmin, Tmean increases with the increase of elevations(3681 m to 4415 m) in the middle reaches of HWYZ. Elevation dependent warming(EDW), the study concluded that magnitudes of Tmin are increasing significantly after the 1990s as compared to Tmax in the HWYZ. It is concluded that the climate of the HWYZ is getting warmer in both sub-basins and the rate of warming was more evident after the 1990s. The outcomes of the study provide an essential insight into climate change in the region and would be a primary index to select and design research scenarios to explore the impacts of climate change on water resources.

Machine Learning Based Psychotic Behaviors Prediction from Facebook Status Updates

With the advent of technological advancements and the widespread Internet connectivity during the last couple of decades,social media platforms(such as Facebook,Twitter,and Instagram)have consumed a large proportion of time in our daily lives.People tend to stay alive on their social media with recent updates,as it has become the primary source of interactionwithin social circles.Although social media platforms offer several remarkable features but are simultaneously prone to various critical vulnerabilities.Recent studies have revealed a strong correlation between the usage of social media and associated mental health issues consequently leading to depression,anxiety,suicide commitment,and mental disorder,particularly in the young adults who have excessively spent time on socialmedia which necessitates a thorough psychological analysis of all these platforms.This study aims to exploit machine learning techniques for the classification of psychotic issues based on Facebook status updates.In this paper,we start with depression detection in the first instance and then expand on analyzing six other psychotic issues(e.g.,depression,anxiety,psychopathic deviate,hypochondria,unrealistic,and hypomania)commonly found in adults due to extreme use of social media networks.To classify the psychotic issues with the user’s mental state,we have employed different Machine Learning(ML)classifiers i.e.,Random Forest(RF),Support Vector Machine(SVM),Naïve Bayes(NB),and K-Nearest Neighbor(KNN).The used ML models are trained and tested by using different combinations of features selection techniques.To observe themost suitable classifiers for psychotic issue classification,a cost-benefit function(sometimes termed as‘Suitability’)has been used which combines the accuracy of the model with its execution time.The experimental evidence argues that RF outperforms its competitor classifiers with the unigram feature set.

AMC Integrated Multilayer Wearable Antenna for Multiband WBAN Applications

In this paper,a compact,efficient and easy to fabricate wearable antenna integrated with Artificial Magnetic Conductor(AMC)is presented.Addition of slots and bevels/cuts in the rectangular monopole patch antenna yield a wide bandwidth along with band notches.The proposed antenna is backed with an AMC metasurface that changes the bidirectional radiation pattern to a unidirectional,thus,considerably reducing the Specific Absorption Ratio(SAR).The demonstrated antenna has a good coverage radiating away from the body and presents reduced radiation towards the body with a front-to-back ratio of 13 dB and maximum gain of 3.54 dB.The proposed design operates over a wide frequency band of 2.9 to 12 GHz(exceeding the designated 3.1−10.6 GHz Ultra-Wideband(UWB)band).The band notches were created using slots on the radiating patch in the sub-bands from 5.50 to 5.67 GHz and 7.16 to 7.74 GHz.The overall dimensions of the structure are 33×33×6.75 mm3.The antenna’s radiation performance increased considerably with the addition of the AMC layer.The SAR values for the antenna are reduced by 85.3%when the AMC is used and are 0.083 W/kg which is well below the FCC SAR limits.The simple design,miniaturized profile,low SAR and wide operating bands with multiple band notches make the presented antenna an appealing choice for several UWB wearable body area network(WBAN)applications.

Hybrid Metamodeling/Metaheuristic Assisted Multi-Transmitters Placement Planning

With every passing day,the demand for data traffic is increasing,and this urges the research community not only to look for an alternating spectrum for communication but also urges radio frequency planners to use the existing spectrum efficiently.Cell sizes are shrinking with every upcoming communication generation,which makes base station placement planning even more complex and cumbersome.In order to make the next-generation cost-effective,it is important to design a network in such a way that it utilizes the minimum number of base stations while ensuring seamless coverage and quality of service.This paper aims at the development of a new simulation-based optimization approach using a hybrid metaheuristic and metamodel applied in a novel mathematical formulation of the multi-transmitter placement planning(MTPP)problem.We first develop a new mathematical programming model for MTPP that is flexible to design the locations for any number of transmitters.To solve this constrained optimization problem,we propose a hybrid approach using the radial basis function(RBF)metamodel to assist the particle swarm optimizer(PSO)by mitigating the associated computational burden of the optimization procedure.We evaluate the effectiveness and applicability of the proposed algorithm by simulating the MTPP model with two,three,four and five transmitters and estimating the Pareto front for optimal locations of transmitters.The quantitative results show that almost maximum signal coverage can be obtained with four transmitters;thus,it is not a wise idea to use higher number of transmitters in the model.Furthermore,the limitations and future works are discussed.

Leveraging the Role of Dynamic Reconfigurable Antennas in Viewpoint of Industry 4.0 and Beyond

Industry 4.0 is a digital paradigm that refers to the integration of cutting-edge computing and digital technologies into global industries because of which the state of manufacturing,communication,and control of smart industries has changed altogether.Industry 4.0 has been profoundly influenced by some major disruptive technologies such as the Internet of Things(IoT),smart sensors,machine learning and artificial intelligence,cloud computing,big data analytics,advanced robotics,augmented reality,3D printing,and smart adaptive communication.In this review paper,we discuss physical layer-based solutions with a focus on high reliability and seamless connectivity for Industry 4.0 and beyond applications.First,we present a harmonized review of the industrial revolution journey,industrial communication infrastructure,key performance requirements,and potential sub-6-GHz frequency bands.Then,based on that,we present a comprehensive review of intelligent tunable dynamic antenna systems at sub-6 GHz as key enablers for next-generation smart industrial applications.State-of-the-art smart antenna techniques such as agile pattern reconfigurability using electrical components,machine learning-and artificial intelligence-based agile beam-scanning antennas,and beam-steerable dynamic metasurface antennas are thoroughly reviewed and emphasized.We unfolded the exciting prospects of reconfigurable dynamic antennas for intelligent and reliable connectivity in application scenarios of Industry 4.0 and beyond such as Industrial IoT and smart manufacturing.

Rate optimization using low complex methods with reconfigurable intelligent surfaces

With the help of a developing technology called reconfigurable intelligent surfaces(RISs),it is possible to modify the propagation environment and boost the data rates of wireless communication networks.In this article,we optimized the phases of the RIS elements and performed a fair power allocation for each subcarrier over the full bandwidth in a single-input-single-output(SISO)wideband system where the user and the access point(AP)are provided with a single antenna.The data rate or its equivalent channel power is maximized by proposing different low-complex algorithms.The strongest tap maximization(STM)and power methods are compared with the semidefinite relaxation(SDR)method in terms of computational complexity and data rate performance.Runtime and complexity analysis of the suggested methods are computed and compared to reveal the actual time consumption and the required number of operations for each method.Simulation results show that with an optimized RIS,the sum rate is 2.5 times higher than with an unconfigured surface,demonstrating the RIS's tremendous advantages even in complex configurations.The data rate performance of the SDR method is higher than the power method and less than the STM method but with higher computational complexity,more than 6 million complex operations,and 50 min of runtime calculations compared with the other STM and power optimization methods.

Intelligent wireless walls for contactless in-home monitoring

Human activity monitoring is an exciting research area to assist independent living among disabled and elderly population.Various techniques have been proposed to recognise human activities,such as exploiting sensors,cameras,wearables,and contactless microwave sensing.Among these,the microwave sensing has recently gained significant attention due to its merit to solve the privacy concerns of cameras and discomfort caused by wearables.However,the existing microwave sensing techniques have a basic disadvantage of requiring controlled and ideal settings for high-accuracy activity detections,which restricts its wide adoptions in non-line-of-sight(Non-LOS)environments.Here,we propose a concept of intelligent wireless walls(IWW)to ensure high-precision activity monitoring in complex environments wherein the conventional microwave sensing is invalid.The IWW is composed of a reconfigurable intelligent surface(RIS)that can perform beam steering and beamforming,and machine learning algorithms that can automatically detect the human activities with high accuracy.Two complex environments are considered:one is a corridor junction scenario with transmitter and receiver in separate corridor sections and the other is a multi-floor scenario wherein the transmitter and receiver are placed on two different floors of a building.In each of the aforementioned environments,three distinct body movements are considered namely,sitting,standing,and walking.Two subjects,one male and one female perform these activities in both environments.It is demonstrated that IWW provide a maximum detection gain of 28%in multi-floor scenario and 25%in corridor junction scenario as compared to traditional microwave sensing without RIS.