In this paper, we are presenting an epidemiological model for exploring the transmission of outbreaks caused by viral infections. Mathematics and statistics are still at the cutting edge of technology where scientific experts, health facilities, and government deal with infection and disease transmission issues. The model has implicitly applied to COVID-19, a transmittable disease by the SARS-CoV-2 virus. The SIR model (Susceptible-Infection-Recovered) used as a context for examining the nature of the pandemic. Though, some of the mathematical model assumptions have been improved evaluation of the contamination-free from excessive predictions. The objective of this study is to provide a simple but effective explanatory model for the prediction of the future development of infection and for checking the effectiveness of containment and lock-down. We proposed a SIR model with a flattening curve and herd immunity based on a susceptible population that grows over time and difference in mortality and birth rates. It illustrates how a disease behaves over time, taking variables such as the number of sensitive individuals in the community and the number of those who are immune. It accurately model the disease and their lessons on the importance of immunization and herd immunity. The outcomes obtained from the simulation of the COVID-19 outbreak in India make it possible to formulate projections and forecasts for the future epidemic progress circumstance in India.

Healthcare applications of IoT systems have gained huge popularity across the globe. From personal monitoring to expert clinical diagnosis, healthcare IoT systems have shown their importance to all possible extents. The ease of use and precise results add to the wide acceptance of such systems. However, this has also led to a magnificent increase in the number of attacks aimed at stealing or manipulating data as well as operations of HIoT-based healthcare assistance. Among the various modes of attacks, network-based attacks are found in the majority. In this work, we perform a critical review of these attacks, the existing countermeasures, and their limitations to understand and proclaim the importance of securing healthcare networks in the best possible manner. We also emphasize the necessity of deep learning-based smart solutions for securing healthcare systems, understanding the potential of deep learning in the security aspects being deployed in other genres of IoT applications. A comparative analysis of deep learning and machine learning-based security solutions is performed to examine their performances.

Stronger defense mechanisms are needed for the safety of healthcare IoT systems, for faster detection and smooth recovery from cyber-attacks, without disrupting services. This study addresses the need to safeguard healthcare IoT systems through efficient detection of potential anomalies leveraging the capacities of deep learning, and also rolling back the system to the safest checkpoint in the recent past, verified using post-quantum verification using ML-DSA/CRYSTALS-Dilithium. A two-tier architecture is proposed in this study with deep anomaly detection and attack severity analysis in the first tier, and post-quantum verification for selecting a policy-driven safe rollback point based on multi-factor assessment, with due consideration of risks. The reinforcement learning-based framework is used in the checkpoint selection phase that selects the checkpoint with the best Q-Score. The model is implemented over two prominent HIoT network datasets–WUSTL EHMS 2020 and CIC IoMT 2024. The model is evaluated using anomaly detection metrics (attack probability, confidence score, severity analysis, and recovery uptime), trust score, verification latency, recovery time, rollback quality, and performance metrics (F1-score, false-positive rate, precision, and recall). The proposed model achieved strong overall performance across both healthcare IoT datasets, with average values of 59.23% attack probability, 94.00% confidence, 5.61% anomaly score, 69.50% severity, 26.61 ns recovery time, 75.86% trust score, 98.37% uptime, 72.93% rollback quality, 11.28 ns verification latency, 98.37% F1-score, 98.28% recall, 98.4% precision, and 0.045% false positive rate. The proposed model effectively and accurately detects an attack and proposes the suitable recovery method–micro rollback, medium rollback, or complete rollback- based on the attack severity analysis. Better system uptime is ensured by selecting recent and trustworthy checkpoints to roll back based on post-quantum verification and combined trust score calculation.