In the communication model of the OSI layer, the Media access control (MAC) layer has been given higher priority than other layers. It is a sub-layer of the data link layer, mainly controlling the physical equipment and interacting with the channels over the Internet of Things (IoT) sensor nodes. Mac layers have used two protocol types: contention-based and contention-free during transmission. These two protocols have controlled the physical equipment and data transmission for the last decade. Yet in the MAC layers transmission, some challenging issues are complicated to resolve. Data collisions are the significant changing issues at the MAC layer. As per the survey of researchers, the contention-based protocol is more affected by collision due to allowing the sharing of channels to all nodes over networks. As a result, it has got message delay, demanding more energy, data loss, and retransmission. The researcher always focuses on reducing collision during transmission to overcome these issues. They mainly evaluate the priority-based collision control using the contention-based protocol. In this ANTMAC model, we have considered the lower energy nodes’ priority to enhance the likelihood that a node will gain access to the transmission channel before its power and batteries run out. Our recommended method ANTMAC outperforms ECM-MAC in terms of content retrieval time (CRT), total no of retransmission (TNR), total energy consumption (TEcm), throughput and network lifetime (NLT).

Higher Order Neural Networks (HONN) are characterized with fast learning abilities, stronger approximation, greater storage capacity, higher fault tolerance capability and powerful mapping of single layer trainable weights. Since higher order terms are introduced, they provide nonlinear decision boundaries, hence offering better classification capability as compared to linear neuron. Nature-inspired optimization algorithms are capable of searching better than gradient descent-based search techniques. This paper develops some hybrid models by considering four HONNs such as Pi-Sigma, Sigma-Pi, Jordan Pi-Sigma neural network and Functional link artificial neural network as the base model. The optimal parameters of these neural nets are searched by a Particle swarm optimization, and a Genetic Algorithm. The models are employed to capture the extreme volatility, nonlinearity and uncertainty associated with stock data. Performance of these hybrid models is evaluated through prediction of one-step-ahead exchange rates of some real stock market. The efficiency of the models is compared with that of a Radial basis functional neural network, a multilayer perceptron, and a multi linear regression method and established their superiority. Friedman’s test and Nemenyi post-hoc test are conducted for statistical significance of the results.