The Internet of Things (IoT) and cloud computing have revolutionized the technological era unabatedly. These technologies have impacted our lives to a great extent. The traditional cloud model faces a variety of complications with the colossal growth of IoT and cloud applications, such as network instability, reduced bandwidth, and high latency. Fog computing is utilized to get around these problems, which brings IoT devices and cloud computing closer. Hence, to enhance system, process, and data performance, fog nodes are planted to disperse the load on cloud servers using fog computing, which helps reduce delay time and network traffic. Firstly, in this article, we highlight the various IoT–fog–cloud models for distributing the load uniformly. Secondly, an efficient solution is provided using fog computing for balancing load among fog devices. A performance evaluation of the proposed mechanism with existing techniques shows that the proposed strategy improves performance, energy consumption, throughput, and resource utilization while reducing response time.

Cloud computing utilizes enormous clusters of serviceable and manageable resources that can be virtually and dynamically reconfigured in order to deliver optimum resource utilization by exploiting the pay-per-use model. However, concerns around security have been an impediment in the extensive adoption of the cloud computing model. In this regard, advancements in cryptography, accelerated by the wide usage of the internet worldwide, has emerged as a key area in addressing some of these security concerns. In this document, a hybrid cryptographic protocol deploying Blowfish and Paillier encryption algorithms has been presented and its strength compared with the existing hybrid Advanced Encryption Standard (AES) and Rivest Shamir Adleman (RSA) techniques. Algorithms for secure data storage protocol in two phases have been presented. The proposed hybrid protocol endeavors to improve the power of cloud storage through a decrease in computation time and cipher-text size. Simulations have been carried out with Oracle Virtual Box and Fog server used on an Ubuntu 16.04 platform. This grouping of asymmetric and homomorphic procedures has demonstrated enhanced security. Compression usage has helped in decreasing the storage space and computation time. Performance analysis in terms of computation overhead and quality of service parameters like loads of parameters with and without attacks, throughput, and stream length for different modes of block cipher mode has been carried out. Security analysis has been carried out by utilizing the Hardening Index as an audit parameter using Lynis 2.7.1. Similarly, for halting the aforementioned approaches and for regulating traffic, firewall protection has been generated in the chosen hybrid algorithms. Finally, enhancements in the performance of the Paillier and Blowfish hybrid scheme with and without compression compared to the existing schemes using RSA and AES procedures have been demonstrated.

In recent times, the coronavirus (COVID-19) epidemic is becoming a prevalent danger for humankind all over the world. This disastrous virus is propagating very fast through direct contact and respiratory droplets due to its contagious nature, and infecting millions of people globally. In the current scenario, spreading awareness regarding detection, forecasting, and prevention of this pandemic can save numerous lives in the whole community. In the present work, an outburst of this ailment has been investigated from 25/01/2020 to 05/06/2020 and predictions are made for the pattern of this outbreak in the weeks to come. ARIMA and Regression models are employed for forecasting, data being taken from John Hopkin University source for the timeline of 5-month in the year 2020. The error estimation of the proposed models has been carried out with the help of RMSLE and found to be 1.82 and 2.13 for Regression and S-ARIMA models respectively. It is anticipated that there may be a sharp rise in active cases around the world and governmental forms are required to take some stringent steps to stop the spread of this virus. The present study will be highly beneficial for the Governing bodies and health organizations in formulating concrete plans for the near future and long-term span.

Breast cancer is an increasingly serious problem in contemporary society, with millions of women and men worldwide affected by the disease. While traditional cancer detection strategies are at times effective, they typically require costly and time-intensive methods for implementation. The major drawback of using conventional methods for identifying breast cancer using the available data sets is that a single algorithm is not sufficient for accurate breast cancer diagnosis due to the heterogeneity of tumors, diverse data types, pattern complexity, feature engineering and dataset overfitting. The aim is to surpass the constraints of the conventional models and develop a hybrid model. The idea is to attain higher accuracy and lower computational time than existing models. This paper presents a novel approach that combines a one-dimensional convolutional neural network (1D CNN) with long short-term memory (LSTM) for breast cancer diagnosis as the model leverages the strengths of both approaches in extracting sequential features from local data and modelling temporal dependencies and long-range relationships. To detect and classify breast cancer, the 1D CNN and LSTM are used to automatically extract and analyze features from distinguishing features from a real dataset generated from mammography reports. The proposed model is evaluated on the extracted feature of the primary available dataset consisting of mammograms from over 760 patients. The developed model achieves 99% accuracy on the test data, demonstrating its potential to provide an automated approach to breast cancer detection. The work emphasizes a significant improvement in feature extraction, accuracy, and robustness. Additionally, the proposed model’s versatility allows it to handle diverse data types, achieve better generalization and lower computational time. The model offers a high level of interpretability, which is crucial for medical professionals to understand and trust the decisionmaking process of the system. The developed hybrid model outperforms various other state-of-the-art techniques like ANN, CNN, CNN-Bi-LSTM-GRU-AM (Convolutional Neural Network-Bidirectional Long Short-Term Memory-Gated Recurrent Unit-Attention Mechanism), and CNN-GRU (Convolutional Neural Network- Gated Recurrent Unit) in terms of accuracy, feature extraction and computational time. This work emphasises the potential of 1D CNN augmented with LSTM to create an automated system for identifying breast cancer. Hence, provides a promising foundation for further development and practical usage of deep learning for automated cancer diagnosis.