Cancer’s staggering molecular heterogeneity demands innovative approaches beyond traditional single-omics methods. The integration of multi-omics data, spanning genomics, transcriptomics, proteomics, metabolomics and radiomics, can improve diagnostic and prognostic accuracy when accompanied by rigorous preprocessing and external validation; for example, recent integrated classifiers report AUCs around 0.81–0.87 for difficult early-detection tasks. This review synthesizes how artificial intelligence (AI), particularly deep learning and machine learning, bridges this gap by enabling scalable, non-linear integration of disparate omics layers into clinically actionable insights. We explore cutting-edge AI methodologies, including graph neural networks for biological network modeling, transformers for cross-modal fusion, and explainable AI (XAI) for transparent clinical decision support. Critical applications are highlighted, such as AI-driven therapy selection (e.g., predicting targeted therapy resistance), proteogenomic early detection, and radiogenomic non-invasive diagnostics. We further address translational challenges: data harmonization, batch correction, missing data imputation, and computational scalability. Emerging trends, federated learning for privacy-preserving collaboration, spatial/single-cell omics for microenvironment decoding, quantum computing, and patient-centric “N-of-1” models, signal a paradigm shift toward dynamic, personalized cancer management. Despite persistent hurdles in model generalizability, ethical equity, and regulatory alignment, AI-powered multi-omics integration promises to transform precision oncology from reactive population-based approaches to proactive, individualized care.

Now a days Novel Coronavirus named COVID-19 becomes major health concern causing severe health issue in human beings and it becomes a pandemic. It’s a kind of zoonotic that means it can transmit animals to humans. It may spread via polluted hands or metals. No specific treatment is available so far for COVID-19, so initial identification and preventions for COVID-19 will be crucial to control or to break down the chain of COVID-19. For this purpose, we have proposed a fuzzy inference system to diagnose the COVID-19 disease by taking six input factor like as; Ethanol, Atmospheric Temperature (AT), Body Temperature (BT), Breath Shortness (BS), Cough and Cold and the output factor has divided into three linguistic categories which denotes the severity level of the infected patients.

Linear variable parameter systems (LPV) are a very special class of nonlinear systems, which are suitable for controlling dynamic systems with parameter changes. Therefore, in this thesis, the problem of using variable parameter linear systems for controller design and stability analysis is raised. A designed controller must be able to reduce the adverse effects of disturbances in the output, for this purpose, in this research, by creating a compromise between the two functions of \(H_{2}\) and \(H_{\infty }\) and combining them with the anticipatory control of the resistant model, a suitable method can be used to eliminate the effect A disturbance was achieved. The controller designed in this research, while stabilizing the system, in the presence of external disturbance, reduces the effect of external disturbance on the output under the control of the system. In general, the purpose of presenting this research is to provide an effective algorithm for controlling a variable parameter linear system with disturbance using the robust model predictive control method, which method presented in this thesis is based on solving the linear matrix inequality, also the proposed method has the ability to consider It has different restrictions on system states and system output. All the results obtained in different sections, including stability analysis, controller performance analysis, are shown using several validated practical examples and their effectiveness. In this thesis, solving optimization problems in the environment is done, as well as the case solvers. It is used to obtain auxiliary and controlling matrices.

The aim of this work is to establish a new methodology to tackle the multi-objective transportation problems [MOTP] in a Fermatean fuzzy environment that can deal with all the parameters that possess a conflicting nature. In our research work, we developed a new score function in the context of a fermatean nature for converting fuzzy data into crisp data with the help of the Fermatean fuzzy technique. Then, we introduced an algorithm-based methodology, i.e., the Fermatean Fuzzy Programming approach to tackle transportation problems with multi-objectives. The main purpose of this research work is to give an alternate fuzzy programming approach to handle the MOTP. To justify the potential and validity of our work, numerical computations have been carried out using our proposed methodology.