Cardiovascular diseases (CVD) are a predominant health concern globally, emphasizing the need for advanced diagnostic techniques. In our research, we present an avant-garde methodology that synergistically integrates ECG readings and retinal fundus images to facilitate the early disease tagging as well as triaging of the CVDs in the order of disease priority. Recognizing the intricate vascular network of the retina as a reflection of the cardiovascular system, alongwith the dynamic cardiac insights from ECG, we sought to provide a holistic diagnostic perspective. Initially, a Fast Fourier Transform (FFT) was applied to both the ECG and fundus images, transforming the data into the frequency domain. Subsequently, the Earth Mover’s Distance (EMD) was computed for the frequency-domain features of both modalities. These EMD values were then concatenated, forming a comprehensive feature set that was fed into a Neural Network classifier. This approach, leveraging the FFT’s spectral insights and EMD’s capability to capture nuanced data differences, offers a robust representation for CVD classification. Preliminary tests yielded a commendable accuracy of 84%, underscoring the potential of this combined diagnostic strategy. As we continue our research, we anticipate refining and validating the model further to enhance its clinical applicability in resource limited healthcare ecosystems prevalent across the Indian sub-continent and also the world at large.

Breast carcinoma is the second most common cause of cancer-related deaths. Radiologists often use mammography, a noninvasive and inexpensive imaging tool, for the detection and classification of breast cancer (BC) lesions. However, manual analysis is labor-intensive and prone to diagnostic errors. In this scenario, the large-scale deployment of computer-aided diagnosis using well-trained algorithms could significantly reduce the morbidity and mortality associated with this carcinoma. In this study, we used a similarity metric-based classification of mammograms using graphical (with two different image sizes) and geometrical approaches (with a single image size) for comparison to improve the specificity, sensitivity, and accuracy of BC prediction and triage of patients in the order of disease severity. Both classification techniques use two novel algorithms, hereafter referred to as the normal and hybrid methods, to select representative images from the training sets of healthy and unhealthy groups of mammograms. The normal method identifies a representative image by comparing images within a cohort, whereas the hybrid method adopts a comprehensive approach by comparing images from both cohorts. This study explored the effects of image size and cardinality of the training set. Finally, we explored the uncharted territory of mapping accuracy versus computational expense for the different approaches adopted in the current study.

A novel microstrip patch antenna of size 210 × 205 × 22 ?m3 operating in the terahertz band is proposed. We then perform optimization of the proposed antenna using the Golden Ratio technique to realize an antenna with reduced dimensions and better performance. The optimized nanoantenna has reduced dimensions of 120 × 160 × 14 ?m3 ( ? 71.61 % reduction in volume); improved return loss S11 ( < -45.43 dB); gain ( > 5.29 dBi), and bandwidth (156.9 GHz i.e., 45% more). The results are validated through an equivalent circuit model (ECM) in Advanced Design System (ADS), demonstrating good agreement with the CST Studio results. Next, a human heart-phantom model has been created and tested for each designed scenario. It examines the interactions between the heart tissues and the proposed antenna, and it identifies the substrate material that performs the best. The results show that polytetrafluoroethylene (PTFE) material performs better than other substrates. Additionally, the research includes an analysis of the link budget of terahertz channels in the intrabody nanocommunication networks—a bio-medical application. The findings indicate the feasibility of using nanoantennas for practical in-vivo nanocommunications

Source location privacy (SLP) has been of great concern in WSNs when deployed for habitat monitoring applications and is addressed by employing privacy-preserving routing schemes. However, in the existing works, the attacker is assumed to be passive in nature and backtracks to the source node by eavesdropping on the transmitted messages. The effectiveness of such SLP solutions when faced with an active attack is not yet known and is the purview of the current study. In this regard, we initially introduce a novel hybrid attacker model and then assess the impact of such a model on the location privacy performance of three existing time-to-live (TTL)-based random walk solutions—phantom routing scheme (PRS), source location privacy using randomized routes (SLP-R), and position-independent section-based scheme (PSSLP). The location privacy performance in terms of privacy metrics such as capture ratio, safety period, and entropy. It is observed that PSSLP is affected most by the proposed hybrid model with a 125% increase in capture ratio, 83.58%, and 17.36% respective reduction in safety period and entropy. The results indicate the importance and relevance of such attacks

Automated early breast cancer detection has been credited as a lifesaver. In this work, an innovative approach based on the persistent homology diagram (PHD) is proposed. Every mammogram is processed using topological data analytic methods to generate its PHD and then the resized PHDs are analyzed for similarity using Earth mover's distance (EMD). The mammogram corpora obtained from SRM-Chennai Hospital with requisite clearance are analyzed for preliminary results. EMD from our earlier investigations has shown promising results when implemented independently on mammograms. We believe that knowledge of the topological structures obtained using the persistent diagrams can help identify the important structures and signatures in a mammogram and focus on a relevant region of interest. This additional processing layer can provide some interesting insights to offer while implementing an automated disease-tagging web service for breast cancer. The PHD will form the rationale for devising the strategy aimed to resolve the issue of missed- and misdiagnosis of breast cancer resulting in poor clinical prognosis at the community level. Furthermore, a web service-based or mobile-health approach promises to provide fruganomic point of care disease-tagging to the stakeholders at the bottom-end of the healthcare ecosystems residing in remote locations across the Indian subcontinent. The development of multimodal multisensory computational platforms incorporating digital signals from PHD-based image analytics of mammograms and novel biomarkers will form the rationale for large-scale screening of breast cancer patients at the community level.

This article presents an analytical model and characterization of path loss in a human heart-centric nanoscale network. The frequencies under investigation include the terahertz (THz) band (0.1–10 THz) and the optical band (400–750 THz). The path loss models incorporate the impact of spreading loss from signal propagation and absorption loss caused by different layers in the human heart. The results indicate a dependence of the path loss not only on the thickness of the different layers but also on the frequency of operations. The useful insights obtained from the path loss trends at the explored frequencies can facilitate the deployment of nanosensor networks for heart-centric communications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

A high-resolution double-directional channel measurement in a conference room using an ultra-wideband in-house developed channel sounder at 300 GHz is presented. Analysis of the measurement data demonstrates that several non-trivial multipaths that could be utilized in data transmission are present. This motivates us to investigate further multi-stream propagation in the given scenario, and thus, the average channel capacity in an emulated multi-antenna system is evaluated. This paper also demonstrates a capacity enhancement with passive reflecting surfaces (PRS), which will inspire a site-specific coverage design

Healthcare is a vital sector influencing societal well-being and economic stability. The COVID-19 pandemic has highlighted the critical need for innovative solutions, such as remote monitoring and real-time health tracking, to address emerging challenges. This paper examines the transformative potential of wireless technology in revolutionizing healthcare systems, emphasizing advancements in communication, remote surgeries, patient engagement, and cost efficiency. It explores the role of 6G technology in enabling high-speed data transfer, ultra-reliable connectivity, and low latency, providing the foundation for intelligent, connected healthcare ecosystems. Key challenges, including seamless connectivity, data privacy, and network scalability, are analyzed alongside strategies to overcome them, such as adopting 6G-enabled Internet of Everything (IoE), Intelligent Reflecting Surfaces (IRS) to counter signal blockages, and advanced latency reduction techniques. By reviewing state-of-the-art developments and real-world case studies, the paper demonstrates the indispensable role of wireless technology in enhancing patient outcomes, reducing healthcare costs, and ensuring universal access to high-quality care. It concludes with actionable recommendations for healthcare organizations to embrace these innovations for a resilient and efficient future.

This letter tries to address the fundamental questions on the feasibility of multipath communication and achievable capacity for line-of-sight (LoS), obstructed-line-of-sight (OLoS), and non-line-of-sight (NLoS) scenarios in an outdoor setting for futuristic communication networks. In this context, a relevant measurement campaign at 300 GHz is conducted, and the results are presented in terms of the number of non-trivial propagation paths available for multi-stream data transmission. Encouraged by the obtained results, the average achievable channel capacity for such multi-stream channels is evaluated with and without passive reflecting surfaces (PRS). It is observed a multi-antenna system provides a significant improvement in average capacity compared to a single-antenna system with PRS providing additional enhancement

We analyze the spectral efficiency for millimeter wave downlink with beam misalignment in urban macro scenario. For this purpose, we use a new approach based on the modified Shannon formula, which considers the propagation environment and antenna system coefficients. These factors are determined based on a multi- ellipsoidal propagation model. The obtained results show that under non-line-of-sight conditions, the appropriate selection of the antenna beam orientation may increase the spectral efficiency in relation to the direct line to a user. © 2024 URSI.

Comprehensive double-directional channel measurements at 300 GHz in various usage scenarios in corridor environments, such as Access, Device-to-device (D2D), and Backhaul over 40 different receiver (Rx) positions using an in-house developed channel sounder, are presented. The measurement results are analyzed and validated by ray tracing (RT) simulation. The quasi-optical propagation properties at 300 GHz make an accurate estimation of relatively simple propagation in a corridor environment possible by using ray optics theory. However, even though non-trivial quadruple-bounce specular reflection paths can be identified in both scenarios, propagation phenomena other than reflection exist irrespective of the Rx positions. Thus, to model the propagation mechanism appropriately, a quasi-deterministic (QD) channel model comprising deterministic and random components is also proposed. The results generated using the proposed model are found to agree well with our prior observations and measurement results. Finally, the paper concludes by characterizing and comparing the channel for all the investigated scenarios in terms of path loss (PL) and large-scale parameters (LSP). On analyzing the measurement results using synthesized power spectra, proposed QD model, and evaluated PL and LSP it is observed that the Access and D2D scenarios share almost similar propagation mechanisms. Furthermore, in the Access and Backhaul scenario the LoS is observed to be affected by the unresolvable ceiling-reflected components. This study, across three different scenarios, can aid the design of next-generation communication systems operating in the THz spectrum. © 1963-2012 IEEE.

The rapid spread of the COVID-19 pandemic necessitated unprecedented collective action against coronavirus disease. In this light,we are proposing a novel online platform for the visualization of epidemiological data incorporating social determinants for understanding the patterns associated with the spread of COVID-19. The current AI computational platform combines modeling methodologies along with temporal geospatial visualization of COVID-19 data, providing real-time sharing of graphic analytical simulation of vulnerable hotspots of recurrent (nowcasting) and emergent (forecasting) infections visualized on a spatiotemporal scale on geoportals. The proposed study will be a secondary data analysis of primary data accessed from the national portal (Indian Council of Medical Research (ICMR)) incorporating 766 districts in India. Epidemiological data related to spatiotemporal visualization of the demographic spread of COVID-19 will be displayed using a compartmental socio-epidemiological model, reproduction number R, epi-curve diagrams as well as choropleth maps for different levels of administrative and development units at the district levels.

A comprehensive double-directional channel measurement across 40 receiver (Rx) positions in a corridor using an in-house developed 300 GHz channel sounder is reported. During measurement, two types of antennae - horn and probe with different gain and half power beamwidth (HPBW) are used to investigate the impact of mentioned antenna parameters on signal propagation at 300 GHz. The measurement data is subsequently processed to generate the corresponding angular and delay power spectra for both setups. It is observed that irrespective of the antenna type at the Rx almost a similar number of specular paths can be identified for all the Rx positions. Finally, path loss model parameters are evaluated for both omnidirectional path loss (PL) and line of sight (LoS) PL by fitting the data with two popular existing channel models. It is observed that irrespective of the model the path loss exponent (PLE) is always less when the more directional horn antenna is used while the shadowing effect is lower when a wider HPBW probe antenna is used at the Rx.

Low-power wide-area network (LPWAN) has emerged as a dominating communication technology that offers low-power and wide coverage for the Internet of Things (IoT) applications. However, the direct data transmission approach has a limited network lifetime. Even multihop data transmission experiences many difficulties including high data latency, poor bandwidth utilization, and reduced data throughput. To overcome these challenges, in this article, a recent breakthrough in social networks known as small-world characteristics (SWC) is incorporated into LPWANs. In particular, in this work, small-world LPWANs (SW-LPWANs) are developed by using the reinforcement learning (RL) technique and using different node centrality measures like degree, betweenness, and closeness centrality. Furthermore, the performance of the developed SW-LPWANs is evaluated in terms of energy efficiency (alive/dead devices, and network residual energy) and quality-of-service (QoS) (average data latency, data throughput, and bandwidth utilization) and is compared with that of conventional multihop LPWAN. Finally, to validate the simulation results, similar analyses are performed on the real-field LPWAN testbed. The obtained simulation results confirm that an SW-LPWAN developed by the RL method performs better than other techniques, with 11% more alive devices, 5.5% higher residual energy, 2.4% improved data throughput, and 14% efficient bandwidth utilization compared to the next best method. A similar trend is observed with real-field LPWAN testbed data also.

To realize the potential of the Terahertz band (0.1 - 10 THz) in providing high data rate, low latency, and improved reliability extensive measurement campaigns are the need of the hour. In this context, the current study presents the results from a first-of-its-kind measurement campaign conducted in a corridor and from corridor to room at 300 GHz. The investigated positions consist of both line-of-sight and non-line-of-sight cases. The measurement data is processed to generate the power delay profile and environment-embedded azimuth delay power spectra for the positions under study. A careful analysis of the generated results helps in identifying the dominant specular components for each position using ray tracing. We further confirm the poor penetration property of signals at 300 GHz through regular building materials like concrete and plasterboard. The current results lay the foundation for more extensive analysis to develop a channel model for one of the common yet unexplored indoor scenarios.

The unique attributes and higher frequencies of the THz band (0.1-10 THz) make usage of channel models at lower frequencies impractical. Thus there is an acute need to develop new channel models to realize the potential of THz communication and extensive channel measurements can augment the pace of development. In this regard, a measurement conducted in an indoor corridor at 300 GHz using an in-house channel sounder is presented. The high-resolution three-dimensional measurement data are processed to obtain a double-directional angular delay power spectrum, and the delay and angular power profile to characterize the channel with regards to path loss, delay, and angular spreads. It is observed that the spread parameters are not only distance-dependent but are also influenced by the presence of natural reflectors in the measurement site. The evaluated results are further compared with other results in the literature at the same and lower frequencies. It is observed that while the spread parameters at lower frequencies reasonably agree with the current campaign the path loss values vary noticeably.

A custom Vision Transformer is used for classifying abnormal fundus images and differentiating them from normal ones. The abnormality in images might be due to any of the following six ocular diseases: age-related macular degeneration, cataracts, diabetes, glaucoma, hypertension, and myopia. Three different Vision Transformer architectures with 8, 14, and 24 layers have been used for the classification problem to identify the optimum one. The entire dataset is classified into seven different labels—healthy and six different diseases. The proposed implementation improves on the existing F1-score, precision, sensitivity, and Kappa scores of ocular disease identification presenting a maximum F1-score of 83.49% with 84% sensitivity, 83% precision, and 0.802 Kappa score using Vision Transformer-14.

A newly developed 300 GHz channel sounder is presented followed by a detailed description of test measurements and the subsequent results obtained to validate its working. An elucidation of the high-resolution double-directional channel measurement in a typical conference room scenario precedes the comparison of the results obtained for the current campaign to that obtained from an earlier campaign at 60 GHz for a similar setup. It is observed that a similar number of clusters for both the bands under investigation for all the transmitter (Tx) and receiver (Rx) positions are obtained from the generated power spectra. Any deviation is theorized to be caused either due to the usage of lower measurement bandwidth in the 60 GHz campaign or due to limited elevation expanse in the 300 GHz measurement. To identify the interacting objects (IOs) causing the clusters, environment-embedded angular power spectra (APS) and ray tracing simulations are used. The large-scale parameters (LSPs) are also evaluated for both campaigns. It is observed that signal propagation at 300 GHz is dominated more by the line-of-sight (LoS) path compared to 60 GHz. The results are also compared with other similar results from the literature.

Owing to the unique attributes of the terahertz (THz) band (0.1-10 THz) adoption of millimeter and centimeter wave channel models to characterize THz communication seems unrealistic. In this context, a cluster-based channel model using multipath components extracted from measurement data can serve as a crucial step in understanding the propagation characteristics of THz signals. In cognizance of the prior fact, the current work uses the Subgrid CLEAN algorithm to extract the multipath components (MPCs) using the data from a measurement campaign conducted in a typical conference room at 300 GHz. The extracted MPCs were further clustered based on their temporal and spatial characteristics using the K-Power Means (KPM) technique. The effectiveness of the employed extraction technique is validated by comparing the extracted power spectrums (angle and delay) with the measured ones whereas the efficacy of the clustering algorithm is demonstrated by identifying the interacting objects (IOs) causing the same.

In recent years, cluster-based channel models comprising clusters or groups of multipath components (MPCs) have found a lot of acceptance in the research community. However, such models are heavily clustering technique dependent where there is a primary lack of uniformity regarding distance measure or the number of initial parameters. In this work, four clustering techniques, using the same power-weighted MPC distance as the distance measure and having the same number of user-specified initial parameters are introduced. The newly evolved techniques with uniform assumptions are next compared in terms of the average Silhouette coefficient (ASC) to assess their clustering quality in terms of cluster compactness using data from an indoor measurement campaign. Since clustering techniques normally do not consider the propagation environment, the relevance of the clusters generated using the introduced techniques is also assessed with the measurement environment using ambiance-embedded spectra and ray tracing simulation. It is observed that the variation of KPowerMeans whose a priori parameters are environment and spectra-dependent performs better both numerically and qualitatively compared with the other techniques. Furthermore, it is observed that independent of the technique there are always clusters that cannot be verified from the environment irrespective of the ASC value. Thus, it is concluded that numerical measures are only indicative and should be used in conjunction with environment-based assessment for conclusive results.

The widespread use of the Internet of Things (IoT) necessitates large-scale communication among smart IoT devices (IoDs) across a wide geographical area. However, due to the limited radio range and scalability issues of traditional wireless sensor networks, wide-area communication among IoDs is not feasible. As a solution, a low-power wide-area network (LPWAN) is emerging as one of the techniques that can provide long-range communication with minimal power consumption. Nevertheless, the direct data transmission approach will no longer be viable due to its short network lifetime. As such, multihop data routing strategies for LPWANs are proposed in the literature. However, multihop data transmission has several challenges, including increased data latency, energy imbalance, poor bandwidth utilization, and low data throughput. To address these challenges, we propose a novel method that uses the machine learning technique for an energy-efficient and Quality-of-Service (QoS)-aware data transfer based on a recent breakthrough in social networks known as small-world characteristics (SWC). The network having SWC (i.e., low average path length and high average clustering coefficient) uses long-range links to reduce the number of intermediate hops for data transmission. In particular, a Q -learning framework is utilized for introducing optimal long-range links between the selected IoDs, resulting in the development of a small-world LPWAN (SW-LPWAN). Furthermore, the performance of the proposed method is computed in terms of energy efficiency and QoS. Moreover, the results are compared with existing data routing techniques, such as low-energy adaptive clustering hierarchy (LEACH), modified LEACH, conventional multihop, and direct data transmission. Specifically, the proposed method maintains 29% more alive nodes, 18% higher residual energy, and 22% higher data throughput compared to the second-best-performing method. As such, the obtained experimental results validate that the proposed method outperforms other existing methods in the context of energy consumption and QoS.

Fifth generation (5G) new radio is now offering sidelink capability, which allows direct vehicle-to-vehicle (V2V) communication. Millimeter wave (mmWave) enables low-latency mission-critical V2V communications, such as forward crash warning, between two vehicles crossing on a road without dividers. In this article, we present a measurement-based path loss (PL) model for V2V links operating at 59.6 GHz mmWave when two vehicles approach from opposite sides and cross each other. Our model outperforms other existing PL models and can reliably model both approaching and departing vehicle scenarios.

As the world warms up to the idea of millimeter wave (mmWave) communication and fifth generation (5G) mobile networks, realization slowly dawns that the data rate, latency, throughput, and other performance metrics that are used to assess a new wireless communication technology will not be enough to support the demands of envisioned futuristic applications. Thus there is an eagerness to further climb up the frequency ladder to use the large swathes of available spectrum in the 0.1 - 10 THz band which is expected to act as the key technology enabler to fulfill the requirements of the sixth generation (6G) wireless communication and possibly even beyond. Channel measurement and modeling are crucial to the design and deployment of future wireless communication systems and researchers across the globe are putting their best foot forward to accelerate the process. The current article presents comprehensive assimilation of research efforts in the context of THz channel sounding. A detailed overview of the current channel sounding techniques is first introduced followed by their relevance to THz band channel measurement. An in-house novel channel sounder developed for THz band measurement is also briefly introduced in this context. The paper next provides elaborate dissemination of various measurement campaigns in the band of interest followed by the modeling techniques that are available in the literature and are being adopted for the THz band. Post the description of different challenges and future research directions in the context of sounding, measurement, and modeling the article is concluded.

Mammography is an inexpensive and noninvasive imaging tool that is commonly used in detection of breast lesions. However, manual analysis of a mammogramic image can be both time intensive and prone to unwanted error. In recent times, there has been a lot of interest in using computer-aided techniques to classify medical images. The current study explores the efficacy of an Earth Mover’s Distance (EMD)-based mammographic image classification technique to identify the benign and the malignant lumps in the images. We further present a novel leader recognition (LR) technique which aids in the classification process to identify the most benign and malignant images from their respective cohort in the training set. The effect of image diversity in training sets on classification efficacy is also studied by considering training sets of different sizes. The proposed classification technique is found to identify malignant images with up to 80 % sensitivity and also provides a maximum F1 score of 72.73 %.

A transfer learning-based convolutional neural network (CNN) architecture is used in the current study to differentiate parasitic malaria cell images from the healthy ones and localize the parasites in infected images using global average pooling(GAP) and heat map. Malaria is a serious malady that can even lead to death in the absence of timely diagnosis. With the use of computerized malaria diagnosis, the suggested solution tackles the problem of timely detection and eases the strain on health care. Three transfer learning-based neural network architectures are studied and compared in terms of their accuracy, precision, sensitivity and specificity. The optimal model with less number of false negatives was then interfaced with a newly developed web service which can be easily accessed and used by common people. The studied models were trained and evaluated on 27,558 single cell images, yielding a maximum accuracy of 96.88%, with 97.35% sensitivity, 96.41% specificity, 96.89% F1-Score, and 96.44% precision.

Let G be a linear algebraic group over an algebraically closed field k and Autalg(G) the group of all algebraic group automorphisms of G. For every ??Autalg(G) let R(?) denote the set of all orbits of the ? -twisted conjugacy action of G on itself (given by (g,x)?gx?(g?1), for all g,x?G ). We say that G has the algebraic R? -property if R(?) is infinite for every ??Autalg(G). In [1] we have shown that this property is satisfied by every connected non-solvable algebraic group. From a theorem due to Steinberg it follows that if a connected algebraic group G has the algebraic R? -property, then G? (the fixed-point subgroup of G under ? ) is infinite for all ??Autalg(G). In this article we show that the condition is also sufficient. We also show that a Borel subgroup of any semisimple algebraic group has the algebraic R? -property and identify certain classes of solvable algebraic groups for which the property fails.

The huge surge in population over recent years has led to several budding challenges like unemployment, rapid urbanisation and ecological imbalance. The aforementioned issues can be addressed simply by promoting the growth of vegetation and commercial tree plantations in desolated lands leading to overall sustainable development and maintenance of ecological balance. Eucalyptus is one such plant which is easy to grow, can survive in alkaline or saline soils, can support rapid afforestation and has high commercial value. The present study focuses on understanding the relationship between various tree form parameters or characteristics of Eucalyptus Regnans using Machine Learning (ML) techniques such as Support Vector (SV), K-Nearest Neighbours (KNN) and Decision Tree (DT). In comparison to several methods that can be used for a typical data analysis problem, Machine Learning approaches are famed to produce reasonable conclusion by analysing a data pattern. In our current work the above-mentioned algorithms were employed to understand the relationship between various form factors of a tree such as branch form, crown form, diameter at breast height (DBH), and the height of the tree, stem form and vigour and provide suitable insights. The algorithms provide a mathematical approach to understand the dependencies between different tree forms enabling effective monitoring and sustainable growth in plantations.

Low-power wide-area networks (LPWANs) are gaining popularity in the research community due to their low power consumption, low cost, and wide geographical coverage. LPWAN technologies complement and outperform short-range and traditional cellular wireless technologies in a variety of applications, including smart city development, machine-to-machine (M2M) communications, healthcare, intelligent transportation, industrial applications, climate-smart agriculture, and asset tracking. This review paper discusses the design objectives and the methodologies used by LPWAN to provide extensive coverage for low-power devices. We also explore how the presented LPWAN architecture employs various topologies such as star and mesh. We examine many current and emerging LPWAN technologies, as well as their system architectures and standards, and evaluate their ability to meet each design objective. In addition, the possible coexistence of LPWAN with other technologies, combining the best attributes to provide an optimum solution is also explored and reported in the current overview. Following that, a comparison of various LPWAN technologies is performed and their market opportunities are also investigated. Furthermore, an analysis of various LPWAN use cases is performed, highlighting their benefits and drawbacks. This aids in the selection of the best LPWAN technology for various applications. Before concluding the work, the open research issues, and challenges in designing LPWAN are presented.

The fourth industrial revolution mostly revolves around new techniques and concepts such as artificial intelligence (AI), machine learning (ML), internet of things (IoT), etc. The recent spurt of corona virus has wreaked havoc across the globe and led to huge loss of human lives. An intelligent system with innovative technologies can be implemented to address the rapid spread of the deadly virus. In this paper, we present our patented [1] idea of Smart Face Shield (SMAFS) that can not only help to maintain appropriate social distancing in a crowded place but also to identify a person with preliminary symptoms of corona virus.SMAFS is designed as a technically improved face shield to maintain social distancing by appropriate use of proximity sensor and to measure temperature of the wearer by using contact temperature sensor. LED's and buzzer are placed strategically to alert people via visual and audio signals respectively. Such precautionary detection and proximity alert prototype can prove instrumental in early diagnosis and isolation aiding in crowd management and free movement in places of social gathering.

The recent development of Generative Adversarial Networks (GANs) have greatly eased the generation of deepfake images which are indistinguishable from real images. As a downside of such advancement, it is now easy to impersonate a person leading to identity theft and other malicious outcomes. In such a scenario it becomes imperative to have a robust algorithm in place which can segregate real images from the fake ones. In this study, we suggest a residual connection based convolutional neural network (CNN) architecture for detecting deepfake images and compare the results with the existing transfer learning algorithms for identifying the deepfakes. The data set used in this study is the combination of the Flickr-Faces-HQ (FFHQ) data set (Nvidia) and the deepfakes generated by the Style GAN, which is proposed by Nvidia. The data set consisting of 1,20,000 images is used for training and validating the network, while a separate set of 20,000 real world images are used for testing the performance of the model. In this current work, we test the robustness of three different algorithms - Inception Resnet V2, VGGFace2, and our customized Residual CNN with and without cut-out regularization in identifying real images. The residual architecture-based implementation in combination with cut-out architecture produces the lowest false positives rate at 0.0043% while the Inception Resnet V2 in combination with cut - regularization produces the best accuracy at 99.05%.

Pneumonia is an inflammatory condition affecting the small air sacs known as the alveoli present in the lungs. Despite the availability of vaccines for certain types it is known to be one of the leading causes of death across all age groups around the world. Chest X-Ray (CXR) images, blood test or sputum culture are standard techniques primarily used by doctors to confirm their diagnosis but is prone to human error due to huge imbalance between number of potential patients and doctors. Deep learning based computer aided technology with reasonably good accuracy and precision can aid the doctors by eliminating the benign cases. In this paper, a transfer learning based convolutional neural network (CNN) architectures is proposed for classifying CXR images into healthy and pneumonia affected with high accuracy and precision. The proposed method uses three different transfer learning architectures, viz. VGG - 16, VGG - 19 and Inception Resnet V2 for comparison and is found to provide best results with VGG - 19 architecture. An accuracy of 95.82% with 98.55% precision, 96.20% specificity and 95.67% sensitivity are obtained with the help of VGG-19 which is superior to any existing solution known to the authors.

Few convolutional neural networks (CNN) have been trained with a transfer learning method to facilitate either binary classification of radiography images into COVID-19 infected and normal or ternary classification into normal, pneumonia, and COVID-19 infected. As the number of COVID-19 cases grow exponentially, the proposed solution can provide an early home based computer-aided diagnosis to ease the pressure on healthcare. The decision made by the model can advise a patient on whether it is critical to visit a doctor or not. In this paper, a CNN based transfer learning model was used to provide a superior precision in image classification. The neural network model was trained and tested using 1,183 radiography images to report the precision that can be attained in authentic conditions using three different CNNs. The accuracy of the model in classifying radiography images is 97.46% for ternary classification and 99.36% accuracy for binary classification using VGG-16 CNN architecture. In addition, the tested algorithm is also developed as a web application for detecting COVID-19 with Chest X-ray images and deployed in the cloud for public use.

Mammography is one of the primary radiography techniques that is used for detection of breast lesions which may range from benign to malignant pathologies. However manual analysis of a mammogram can be both time intensive and prone to unwanted error. Engineers off late has been actively contributing to the domain of medical image classification to ease the categorization process and make it efficient. This paper introduces a technique to identify the graveness of breast carcinoma from mammograms using three different sized training sets. In the current study we present an Earth Mover's Distance (EMD) based binary classification of mammograms containing benign and malignant tumors. To facilitate the classification, a novel Leader Selection (LS) technique is used to identify the leader of each cohort in the training sets. The proposed model achieves a maximum sensitivity of 93.75% while producing a maximum F1 score of 83.33%. It is also observed that increasing the size of the training set improves the relevant performance metric.

Medical image processing has gained a lot of relevance of late and is turning out to be a boon in different clinical aspects. One such emerging field is brain tumor detection from magnetic resonance images (MRI) of brain. Engineers are actively developing tools to process medical images and aid doctors in with their diagnosis. MRI images are clinical images which are obtained on a computer when a patient goes through MRI scanning done by a respective machine. A brain tumor is a cluster of an abnormal mass of tissue where cell growth is out of control due to an abnormality in the mechanisms that control normal cells. In this work, our main aim is to measure the size of a brain tumor in terms of its diameter and area from a patient's MRI imagery using MATLAB. The proposed method incorporates different layers of noise removal techniques to clean up the images as well as image segmentation and morphological operations for detection and extraction of tumors and determining their size. By measuring the size of the tumor in a patient's brain at regular intervals doctors can diagnose the severity of the tumor in a patient's brain and can administer suitable treatment before it gets malignant.

We study the time-variance of a roadside infrastructure to infrastructure (I2I) channel operating at 60 GHz millimetre wave (mmWave) band, where the time-variance is caused by moving vehicles acting as scatterers. At first, measurement data is obtained by placing the transmitter (TX) and the receiver (RX) at different heights to emulate a link between two nonidentical roadside units (RSUs), and time-domain channel sounding is performed by sending complementary Golay sequences from the TX to the RX. A linear piece-wise interpolation of the corresponding temporal auto-correlation function (ACF) is used to find the Doppler spread of the I2I channel, where our interpolation method compensates for a slower sampling rate. Next, a framework is presented for time-variant channel impulse response (CIR) simulation which focuses on moving scatterers only and validates the linear piece-wise ACF model. The framework is useful for time-variant vehicular I2I channel simulation and in speed estimation related vehicular applications. Finally, a double-slope curve-fitted analytical model for ACF is proposed as a generalisation to the linear piece-wise model. The proposed model and its Doppler spectrum are found to be in agreement with the analytical results for fixed-to-fixed (F2F) channels with moving scatterers and matches perfectly with the measured data.