Search

Wireless networks (WSN) are sometimes inaccessible to humans and can be found in deep forests, diverse risky fields, high-mountainous areas and even underwater environments at least. Owing to continuous or instant changes in environmental parameters, failures in sensor networks are unavoidable. A fault can lead to a misread, which can harm the environment economically and physically. In several primary applications, wireless sensor networks (WSNs), including battlefield control, environmental monitoring and forestry fire monitoring are widely used. Research is being conducted to reduce energy usage, improve the longevity and life of the WSN network. This paper provides an ANFIS method for the summation, based on the neuro-fuzzy optimization model estimator of defect-tolerant WSNs. For WSNs, the scheme proposes the use of an intra-cluster and inter-cluster failure detection estimator adaptive neuro-fuzzy inference system (ANFIS). Traditional detection strategies for malfunction include a centralized mechanism for avoiding failure detection when the principal defect detector fails. In typical methods, the fault nodes are discarded. To solve these problems, we propose the identification and classification of distributed fault nodes by means of adaptive neuro-fuzzy inference method.

Nowadays, so many people are living in world. If so many people are living, then the diseases are also increasing day by day due to adulterated and chemical content food. The people may suffer either from a small disease such as cold and cough or from a big disease such as cancer. In this work, we have discussed on the encephalon tumor or cancer which is a big problem nowadays. If we will consider about the whole world, then there are deficiency of clinical experts or doctors as compared to the encephalon tumor affected person. So, here, we have used an automatic classification of tumor by the help of particle swarm optimization (PSO)-based extreme learning machine (ELM) technique with the segmentation process by the help of improved fast and robust fuzzy C mean (IFRFCM) algorithm and most commonly feature reduction method used gray level co-occurrence matrix (GLCM) that may helpful to the clinical experts. Here, we have used the BraTs (“Multimodal Brain Tumor Segmentation Challenge 2020”) dataset for both the training and testing purpose. It has been monitored that our system has given better classification accuracy as an approximation of 99.47% which can be observed as a good outcome.