renu.rajaram

Research Work: Thesis Title: “Routing in Wireless Mesh Networks” Detailed Description: Network coding is a method of encoding and decoding the transmitted data for the intention of increasing the throughput, reducing the delay there by obtaining robust mesh network and it has been widely used in many networks. In this work, the low network throughput problem faced in WMNs has been tackled using network-coding. In the coding-aware routing protocol design, there are three essential aspects: 1) coding condition, which is used to effectively discover the coding opportunities, and 2) routing metric, which should carefully be designed to facilitate the routing protocol in a simple effective manner 3) The choice of determining the forwarding list and forwarding encoder node. To circumvent all these issues mentioned above, this proposed work helps to address the above issues using any path route metric, code-aware, load-aware route metric and estimation of bandwidth with a network coding to compute the gain of opportunistic transmission. To resolve the decision of which nodes should be included in the forwarding list for sending the encoded packet among all the intersecting nodes to obtain the highest throughput gain, most of the researchers considered the first intersecting node as an encoding node among all the intermediate nodes in wireless mesh networks, in spite of the quality of the first node. The major intention of this work is to consider delay and anypath cost metric in the routing path when deciding the encoding node in the opportunistic routing.

PIONEERING LUNG CANCER DETECTION THROUGH DEEP LEARNING INNOVATIONS This study investigates the use of deep learning techniques to detect lung cancer, a common and deadly disease worldwide. Leveraging advances in artificial intelligence, particularly deep learning, has the potential to improve the accuracy and efficiency of lung cancer diagnosis. In this study, we look at different deep learning models and methodologies to create a robust and reliable system for automatically detecting lung cancer from medical imaging data. The abstract summarizes our methodology, findings, and implications for clinical practice. Objectives:  To explore the effectiveness of deep learning algorithms in the automated detection of lung cancer from medical imaging data.  To develop and optimize deep learning models tailored for lung cancer detection, considering factors such as sensitivity, specificity, and computational efficiency.  To evaluate the performance of the proposed deep learning system against existing methods and clinical standards for lung cancer diagnosis.  To assess the potential impact of the developed system on improving early detection rates, patient outcomes, and overall healthcare efficiency in the management of lung cancer.  This study aims to guide further research and clinical adoption of AI technologies in healthcare by examining the strengths, limitations, and future directions of deep learning for lung cancer detection