Over the course of the last decade, the unmanned aerial vehicle (UAV) research community has received a significant amount of attention. Emergency response operations, such as those that follow a natural disaster, are one of the civil applications that could benefit from the use of UAVs in disaster and crisis management. In the event of a catastrophic event, it would be extremely beneficial for both victims and first responders to have access to a UAV network that is capable of deploying independently and offering communication services. However, when working with complicated situations, one of the most difficult things is coming up with exploratory paths for the networks involved. A crisis and disaster management system using a swarm optimization algorithm (SOA) is proposed to assist in disaster and crisis management. In this system, the UAV search and rescue team follows the strategy called the delay tolerant network, which has the ability to explore. The proposed approach is able to find the global maximum in the search space without ever settling for a suboptimal solution. This work has two primary objectives: the first is to investigate a potential disaster zone, and the second is to direct the UAV to a number of victim groups that were found during the investigation phase. For the purpose of performing a characterization, performance metrics such as delay, throughput, performance rate, and path loss have been analyzed. The results show the superiority of the performance over the existing work.

Sensing devices, high-performance networking, and privacy preservation algorithms have an important role to play in remotely sensed environmental data in smart cities. The data generated by these sensors are heterogeneous, vast, and sensitive. Therefore, it is imperative that adequate security mechanisms are put in place to protect environmental data from privacy breaches and malicious attacks. Prior to data analysis, remotely sensed environmental data, such as weather conditions (windy, cloudy, or rainy), soil types, and other similar data, must be protected. The biggest risks of remotely connected devices are that sensitive information could be leaked and devices could be compromised. Considering these security threats, this paper proposes a Pertinent Privacy Preserving Scheme (P3S). The presented scheme is reliable for sensitive geo-sensed data in thwarting the aforementioned security issues. The data is concealed using two-factor authentication from the transmitter end. In this authentication, the device and receiver's signature are overlapped for improved authentication. The failure in overlapping is identified by delayed signing time and non-coherent agreements. This identification is recurrently analyzed using federated learning. Therefore, the signing process is paused until the device verification is performed. Hence, if the device verification succeeds, then a new data privacy accumulation session is introduced. Contrarily, the accumulation is dropped, preventing compromised actual data from preserving accuracy. In two-factor authentication, lightweight digital signing cryptography is utilized. The proposed scheme maximizes the average authentication success rate and average overlapping factor by 8.86%, and 12.20% respectively. This scheme further reduces average authentication time, false data, and verification time by 10.14%, 9.70%, and 10.19% respectively.

Background/Objectives: Obsessive–Compulsive Disorder (OCD) is a chronic mental health condition characterized by intrusive thoughts and repetitive behaviors. Traditional diagnostic methods rely on subjective clinical assessments, delaying effective intervention. This review examines how advanced neuroimaging techniques, such as Magnetic Resonance Imaging (MRI) and Diffusion Tensor Imaging (DTI), integrated with machine learning (ML), can improve OCD diagnostics by identifying structural and functional brain abnormalities, particularly in the cortico-striato-thalamo-cortical (CSTC) circuit. Methods: Findings from studies using MRI and DTI to identify OCD-related neurobiological markers are synthesized. Machine learning algorithms like Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs) are evaluated for their ability to analyze neuroimaging data. The role of transfer learning in overcoming dataset limitations and heterogeneity is also explored. Results: ML algorithms have achieved diagnostic accuracies exceeding 80%, revealing subtle neurobiological markers linked to OCD. Abnormalities in the CSTC circuit are consistently identified. Transfer learning shows promise in enhancing predictive modeling and enabling personalized treatment strategies, especially in resource-constrained settings. Conclusions: The integration of neuroimaging and ML represents a transformative approach to OCD diagnostics, offering improved accuracy and biologically informed insights. Future research should focus on optimizing multimodal imaging techniques, increasing data generalizability, and addressing interpretability challenges to enhance clinical applicability. These innovations have the potential to advance precision diagnostics and support more targeted therapeutic interventions, ultimately improving outcomes for individuals with OCD.