MANET (Mobile Ad hoc Networks) functionality is determined by routing protocols’ ability to adjust to atypical changes in information and communication technologies, topological systems, and connection status. Due to interference, node migration, the growth of several pathways, security, and propagation loss, MANET network configurations are dynamic. The proactive routing protocol enhances the message flow utilized in the neighborhood discovery process by using the multipoint relays (MPR) approach. In order to increase the protocol’s effectiveness and efficiency while maintaining the OLSR protocol’s reliability, the research presented in this paper proposed an improved OCI-OLSR (Optimized Control Interval-Optimized Link State Routing) that focuses on better control interval management, an advanced MPR selection process, reducing neighbor hold time as well as decreasing flooding. The suggested proposed protocol was examined using the NS3 simulator, and it was compared to the standard OLSR version and AODV(Ad-hoc On-Demand Routing) routing protocol. According to the analysis’s findings, the suggested system has a lot of promise in terms of a variety of performance metrics under diverse conditions. Overall, the article makes the case that the OCI-OLSR protocol may enhance the performance of the regular OLSR protocol in wireless ad hoc networks by addressing a number of the protocol’s flaws.
Pattern recognition is one of the major concerns in the field of machine learning. Appropriate Recognition of patterns leads to addressing the performance concerns. Machine Learning [ML], a subset of Artificial Intelligence [AI] plays an important role in the process of classification, clustering and predictive modeling. This paper focuses on developing a novel classification technique to classify the iris of the plant in order to categorize the flower pattern. An optimized ensemble model is proposed to recognize and categorize the pattern. Initially, Decision Tree, OneR, Adaboost, Random Forest, and Bayesnet models are applied and to improve the performance an ensemble model is proposed.