Maintaining social distance has become one of the most effective alternative measures to prevent infectious illnesses from transmitting throughout the air in crowded areas. Despite its importance, accurately measuring the distance individuals using monocular video feeds remains difficult in everyday circumstances. Problems including viewpoint disorientation, depth ambiguity, and a lack of mechanisms to evaluate risks over time limit the efficacy of numerous modern techniques. To address these issues, the present research introduces M2-DistNet, a cloud-native architecture designed for risk-sensitive social distance tracking utilizing single-focus surveillance video. The entire pipeline is configured on cloud-based GPU infrastructure with event-driven synchronization to a real-time web dashboard for scalable monitoring. Experimental assessment on annotated surveillance datasets shows that M2-DistNet outperforms traditional single-modality methodologies. The method achieves an F1-score of 0.87 and a Mean Absolute Error of $\mathbf{0. 1 9} \mathbf{m}$ while diminishing false positive detections by $\mathbf{5 2 \%}$. The outcomes suggest that the proposed system provides reliable and extensible monitoring. With every aspect taken into consideration, the plan of action has a lot of potential for real-time implementation in volatile public environments.

The emergence of the wireless network as a potentially revolutionary innovation has the ability to change the field of medical diagnostics. This in-depth study aims to explore the various aspects of using the latest wireless technologies to improve the standard of care given to patients and the interactions between patients and healthcare providers. This study investigates a wide range of issues such as patient-centric communication technology, 6G based applications using smart technologies, real-time communication protocols, implementation of artificial intelligence (AI) and blockchain technology in healthcare and the use of wireless devices for remote patient monitoring. 6G wireless communication brings transformative capabilities to healthcare, offering ultra-reliable and low-latency communication (URLLC), improved network capacity, and higher data rates. These advances enable the real-time transmission of critical health data, support complex medical applications, facilitate remote consultations, surgical robotics, and AI-driven diagnostics. This study highlights the significance and implications of combining these concepts in the context of 5G and beyond, paving the way for connected healthcare, personalized medicine, and unprecedented levels of efficiency and innovation. In addition, it also investigates the obstacles and potential associated with the implementation of wireless communication in the healthcare industry. These challenges and opportunities include data security and privacy issues, as well as the need for a robust communication infrastructure. This paper demonstrates the influence that wireless communication has in changing healthcare care delivery, improving patient outcomes, and creating a connected healthcare ecosystem through a careful assessment of current research and case studies in terms of improving quality of services (QoS). The findings of this survey offer important perspectives and recommendations that could aid healthcare professionals, scholars, and governing bodies to efficiently harness the potential of wireless communication to transform patient care and connectivity.

Surveillance systems play a crucial role in detecting suspicious human activities, including attacks, violence, and abductions, in public spaces. This study presents a human intervention-free, hybrid framework that utilizes deep neural networks for real-time theft activity recognition. The proposed methodology employs a dual stream fusion network, combining appearance and motion features, to accurately identify theft actions. Specifically, a modified InceptionV3 model extracts relevant body pose features through keypoint transfer, feeding two separate deep neural network pipelines for appearance and motion analysis. Long-Short-Term Memory network then models temporal relationships between the extracted features across consecutive frames. The novelty of this research lies in the proposed dual-stream fusion architecture, which aims to capture fine-grained temporal and spatial cues for theft detection. A new lab-lifting dataset has also been developed to reflect subtle theft behaviors in academic settings. The framework’s performance is evaluated on a dataset comprising normal and theft activities. The results demonstrate a recognition accuracy of 91.86% , surpassing that of other methods.

Monkeypox is a reemerging viral disease caused by the Monkeypox virus, posing a significant global health threat due to its rapid transmission and lack of widespread diagnostic tools. In the image domain, challenges arise from limited datasets and poor resolution of available images, hampering the development of automated classification and detection systems. To address this, we leveraged a GAN-based approach, specifically Real-ESRGAN, to improve the resolution and quality of a novel dataset comprising 3,165 images. Our model achieved an average SSIM of 0.850 and a PSNR of 33.83 dB, demonstrating its effectiveness in generating high-quality images suitable for training robust detection systems.

Along with healthcare and social media requests, the incorporation of machine learning into sensitive areas has not been as precise as it formerly was. Safety features are also being studied. Errands like performance preparation and induction are increasingly being outsourced to the cloud as cloud computing emerges as a successful computational and multi-person stage. However, due to administrative compliance and safety concerns, this capability is constrained. This work proposes a neural organize category system that uses homomorphic encryption (HE) to protect privacy. The suggested method protects the confidentiality of the customer's query by guaranteeing that buyer records are jumbled during transmission to the cloud and that the jumbled data is returned. In contrast to previous research, this one takes into account the practical difficulties of HE in a secure system and learns about them by adjusting its parameters to control safety and accuracy. We examine scenarios in which parameter selections compromise category accuracy and provide optimal configurations to achieve robust performance. When compared to current methods, exploratory checks on the MNIST dataset reveal completely improved deduction instances for client inquiries, demonstrating the version's practicality and efficiency.

Facial identity recognition is one of the challenging problems in the domain of computer vision. Facial identity comprises the facial attributes of a person’s face ranging from age progression, gender, hairstyle, etc. Manipulating facial attributes such as changing the gender, hairstyle, expressions, and makeup changes the entire facial identity of a person which is often used by law offenders to commit crimes. Leveraging the deep learning-based approaches, this work proposes a one-step solution for facial attribute manipulation and detection leading to facial identity recognition in few-shot and traditional scenarios. As a first step towards performing facial identity recognition, we created the Facial Attribute Manipulation Detection (FAM) Dataset which consists of twenty unique identities with thirty-eight facial attributes generated by the StyleGAN3 inversion. The Facial Attribute Detection (FAM) Dataset has 11,560 images richly annotated in YOLO format. To perform facial attribute and identity detection, we developed the Spatial Transformer Block (STB) and Squeeze-Excite Spatial Pyramid Pooling (SE-SPP)-based Tiny YOLOv7 model and proposed as FIR-Tiny YOLOv7 (Facial Identity Recognition-Tiny YOLOv7) model. The proposed model is an improvised variant of the Tiny YOLOv7 model. For facial identity recognition, the proposed model achieved 10.0% higher mAP in the one-shot scenario, 30.4% higher mAP in the three-shot scenario, 15.3% higher mAP in the five-shot scenario, and 0.1% higher mAP in the traditional 70% − 30% split scenario as compared to the Tiny YOLOv7 model. The results obtained with the proposed model are promising for general facial identity recognition under varying facial attribute manipulation.

The Internet of Things (IoT) has become integral to our daily lives. IoT is tightly governed by the principles of communication and the technologies around it. Thus an in-depth discussion on Communication Technologies and Security Challenges in IoT is required for a professional to design and develop IoT applications. The core aspects that need elaborate discussion are being brought forward in this chapter. It is identified here that three major aspects of IoT Security are vital and require extensive discussion. They are, Communication methodologies and their security challenges, Application areas and approaches addressing several security issues, and the advancements/New trends in IoT communication and related security aspects.

The Internet of Things (IoT) is a rapidly growing network of interconnected devices that has the potential to revolutionize many industries and sectors. However, IoT devices are often vulnerable to security and reliability threats due to their limited resources and the challenging environments in which they are deployed. This study proposes a secure and reliable cognitive radio network (SAR-CRN) architecture for IoT applications. Leveraging cognitive radio (CR) capabilities, SAR-CRN enables efficient spectrum sharing between primary users and resource-limited IoT devices. We propose a two-step relay selection scheme that identifies the optimal relay node capable of correctly decoding the information and retransmitting it with the highest secrecy rate. More specifically, this scheme optimizes relay selection for enhanced security and reliability within the SAR-CRN framework. The performance of the proposed SAR-CRN system is evaluated using a variety of metrics, including the probability of correct decoding ability, and the average secrecy capacity (ASC) and secrecy outage probability (SOP) under both known and unknown channel state information (CSI) scenarios. The result analysis demonstrates that the proposed SAR-CRN system significantly outperforms conventional CR networks (CRNs) in terms of security and reliability, paving the way for secure and reliable communication in resource-constrained IoT environments.

Autism spectrum disorder is a developmental condition that affects the social and behavioral abilities of growing children. Early detection of autism spectrum disorder can help children to improve their cognitive abilities and quality of life. The research in the area of autism spectrum disorder reports that it can be detected from cognitive tests and physical activities of children. The present research reports on the detection of autism spectrum disorder from the facial attributes of children. Children with autism spectrum disorder show ambiguous facial expressions which are different from the facial attributes of normal children. To detect autism spectrum disorder from facial images, this work presents an improvised variant of the YOLOv7-tiny model. The presented model is developed by integrating a pyramid of dilated convolutional layers in the feature extraction network of the YOLOv7-tiny model. Further, its recognition abilities are enhanced by incorporating an additional YOLO detection head. The developed model can detect faces with the presence of autism features by drawing bounding boxes and confidence scores. The entire work has been carried out on a self-annotated autism face dataset. The developed model achieved a mAP value of 79.56% which was better than the baseline YOLOv7-tiny and state-of-the-art YOLOv8 Small model.

The complexity of successive interference cancellation at the receiver’s end is a challenging issue in conventional non-orthogonal multiple access assisted massive wireless networks. The computational complexity of decoding increases exponentially with the number of users. Further, under realistic channel conditions, a synchronous non-orthogonal multiple access scheme is impractical in the uplink device-to-device communications. In this paper, an asynchronous non-orthogonal multiple access-based cyclic triangular successive interference cancellation scheme is proposed for a massive device-to-device network. The proposed scheme reduces the decoding complexity, energy consumption, and bit error rate of a superimposed signal received in an outband device-to-device network. More specifically, the scheme follows three consecutive stages; optimization, decoding, and re- transmission. In the optimization stage, a dual Lagrangian objective function is defined to maximize the number of data symbols decoded at the receiver by determining an optimal interference cancellation triangle, under the co-channel interference and data rate constraints. In the decoding stage, the data in the optimal interference cancellation triangle is decoded using a conventional triangular successive interference cancellation technique. Next, the remaining users’ data are decoded in sequential iterations of the proposed scheme, using the retransmissions from such users. Utilizing the successive interference cancellation characteristics, the performance of the proposed device-to-device network is defined in terms of energy efficiency, bit error rate, computational complexity, and decoding delay metrics. Moreover, the performance of the proposed decoding scheme is compared with the conventional triangular successive interference cancellation decoding scheme to demonstrate the superiority of the proposed scheme.

The technologies used in underwater and air–water (A–W) wireless communication networks (WCN) are increasingly attracting attention due to numerous modern applications, e.g., internet of underwater things etc. However, for practical implementations of these modern applications, the security of the underwater and A–W WCNs needs to be ensured beforehand. Thus, the main focus of this survey is to systematically discuss the security needs of underwater and A–W WCNs, and solutions proposed to date. Before extending our discussion on security, we initially cover the fundamentals of underwater and A–W WCNs. First, we provide a comprehensive overview of different underwater communication technologies: radio frequency (RF), acoustic, optical, and magnetic induction (MI) in terms of channel characteristics, merits, and demerits. The discussion is further extended to A–W wireless communication by presenting direct and indirect (relay-aided) techniques. Then we present the primer on information security which highlights the four fundamental properties of security (i.e., confidentiality, integrity, authentication, and availability) and security solutions (i.e., cryptography and physical layer security) built for the considered underwater communication technologies. In addition, we discuss at length the security aspects of the underwater and A–W WCNs by reviewing and summarizing the existing work in the literature. We notice that the related work on security of RF-based, magnetic induction-based underwater WCNs, and A–W WCNs is practically non-existent. Thus, we highlight this research gap in the literature, and propose a few additional security-related open problems too, that we believe deserve to receive more attention from the underwater, marine, and oceanic research community.

Network slicing is a layer of virtualization of different services of a wireless communication network. The network slicing has its own logical network designed through a larger physical network via the automated allocation of bandwidth, quality of service (QoS) and other network functions. In this paper, we first review the existing Unmanned Aerial Vehicle (UAV)-enabled wireless networks for virtualization and slicing functions in the literature to date and then state a few future UAV-enabled wireless networks that are suitable for upcoming applications and technologies including smart grids, remote surgery, autonomous cars, terahertz communication, wireless power transfer, re-configurable intelligent Surfaces.

The accurate estimation of underwater Visible Light Communication (VLC) channel conditions is challenging due to its widespread attenuation and scattering effects. The channel attenuation is a linear function of frequency and causes exponential signal power loss whereas due to the scattering effect, numerous photons are statistically generated as light beams strike water molecules and there arise security concerns. Assuming realistic underwater conditions, this paper investigates the security performance of a typical Non-Orthogonal Multiple Access (NOMA)-assisted underwater VLC system. It consists of a Floating Vehicle Transmitter (FVT), equipped with multiple Light Emitting Diodes (LEDs) to transmit the signal to two legitimate near-end and far-end Underwater Vehicles (UVs) in presence of an active/passive eavesdropper. The Channel State Information (CSI) of each transmitting link is estimated with the use of a Minimum Mean Square Error (MMSE) technique. Furthermore, we propose a LED selection mechanism to select an LED that can achieve the highest secrecy rate defined under the constraints of known and unknown CSI of legitimate and/or eavesdropping links. Using the Successive Interference Cancellation (SIC) technique, a novel closed-form secrecy outage probability expressions for the conventional single-LED and multi-LED NOMA-VLC links for both known and unknown CSI scenarios is derived. The security performance of the proposed multi-LED NOMA-VLC system is compared with the conventional single-LED NOMA-VLC system under the effect of air bubbles for both fresh and salty water. Finally, we verify the validity of the numerical results through Monte-carlo simulation analysis.

Security issue in underwater visible light communication (UVLC) arises mainly due to the scattering effect wherein numerous photons are statistically generated when a light beam strikes a water molecule. This paper considers an underwater communication scenario wherein a floating vehicle (FV) transmitter that is equipped with multiple light-emitting diodes (LEDs) communicates with the two legitimate near-end and far-end underwater vehicles (UVs) in presence of an eavesdropper. In particular, two non-orthogonal multiple access (NOMA) technology-based optimal LED selection (OLS) and suboptimal LED selection (SLS) schemes are proposed to select a LED that can transmit the information with the highest secrecy rate against active/passive eavesdropping attacks. Furthermore, the FVT transmits the information to both UVs with the selected LED only. Utilizing the successive interference cancellation (SIC) characteristic, this paper derives the closed-form secrecy outage probability expressions for both single-LED and multi-LED transmission strategies for both known and unknown CSI. The security performance of the proposed multi-LED NOMA-UVLC is compared with the conventional single-LED NOMA-UVLC under the effects of air bubbles for both fresh and salty water types. In addition, the validity of the numerical results is verified through Monte-carlo simulation analysis.

In this article, we investigate the physical layer security in an indoor environment, wherein both visible light communication (VLC) as well as radio frequency (RF) technologies are codeployed. We explore the benefits of employing both technologies by imposing a limit of positive secrecy rate to prevent the eavesdropping attacks, which is an important metric in designing a secure wireless network. The VLC technology is used as a primary technology and the RF technology is used when the primary technology cannot satisfy the imposed limit. In particular, a novel secure-link selection mechanism is proposed to select the secure technology (i.e., either VLC or RF technology) based on the availability or nonavailability of instantaneous channel state information of both legitimate and eavesdropping links. The performance of the system is evaluated in terms of average secrecy capacity, connection outage probability, and secrecy outage probability. We observe the effect of various physical parameters on the security performance of the network. Further, analytical results are corroborated with the computer simulation results.

We investigate the physical layer security of decode-and-forward-relayed free space optics (FSO)/radio frequency (RF) communication system. In this network, the eavesdropper exists after relay node and overhears RF transmission. Further, FSO being a line-of-sight transmission is assumed to be secure from eavesdroppers. Here, we have the Gamma-Gamma () distribution for FSO link and generalized eta-mu distribution for RF link. The security for information transmission to the legitimate user in the presence of an eavesdropper is measured in terms of secrecy capacity and secrecy outage probability. Deriving the probability density function and cumulative distribution function of end-to-end signal-to-noise ratio, the closed-form expressions for security parameters are achieved. The numerical analysis of the proposed system is done under the influence of atmospheric turbulence effects and various fading conditions. The results have been verified through simulation.

SummaryWe investigate the physical layer security of decode‐and‐forward–relayed free space optics (FSO)/radio frequency (RF) communication system. In this network, the eavesdropper exists after relay node and overhears RF transmission. Further, FSO being a line‐of‐sight transmission is assumed to be secure from eavesdroppers. Here, we have the Gamma‐Gamma (ΓΓ) distribution for FSO link and generalized η−μ distribution for RF link. The security for information transmission to the legitimate user in the presence of an eavesdropper is measured in terms of secrecy capacity and secrecy outage probability. Deriving the probability density function and cumulative distribution function of end‐to‐end signal‐to‐noise ratio, the closed‐form expressions for security parameters are achieved. The numerical analysis of the proposed system is done under the influence of atmospheric turbulence effects and various fading conditions. The results have been verified through simulation.