No abstract

No abstract

In recent years, underwater wireless sensor networks (UWSNs) have been widely applied to aquatic and military applications. Network survivability is an essential attribute to be considered in UWSN circumstance and various stratifications like node survivability, connectivity and rapid fault node detection and recovery. However, efficient and accurate fault tolerance mechanisms are required to prolong the network survivability in UWSN. In this research work, the energy-efficient fault detection and recovery management (EFRM) approach is proposed for the UWSN with relatively better network survivability. The hidden Poisson Markov model has been incorporated in EFRM to achieve efficient fault detection throughout the whole network. Thereafter, the recovered node can be selected by using the analytical network process model which facilitates to recover the larger number of nodes in the damaged region. The simulation results manifest that when the fault probability is 40%, the detection accuracy of the proposed EFRM is over 99%, and the false positive rate is below 2%. The detection accuracy is improved by up to 12% when compared with the existing state-of-the-art schemes.

In today’s world, brain stroke is considered as a life-threatening disease provoked by undesirable blockage among the arteries feeding the human brain. The timely diagnosis of this brain stroke detection in Magnetic Resonance Imaging (MRI) images increases the patient’s survival rate. However, automated detection plays a significant challenge owing to the complexity of the shape, dimension of size and the location of stroke lesions. In this paper, a novel optimized fuzzy level segmentation algorithm is proposed to detect the ischemic stroke lesions. After segmentation, the multi-textural features are extracted to form a feature set. These features are given as input to the proposed weighted Gaussian Naïve Bayes classifier to discriminate normal and abnormal stroke lesion classes. The experimental result manifests that the proposed methodology achieves a higher accuracy as compared with the existing state-of-the-art techniques. The proposed classifier discriminates normal and abnormal classes efficiently and attains 99.32% of accuracy, 96.87% of sensitivity and 98.82% of F1 measure.

Wireless sensor network (WSN) consists of a large amount of limited battery-powered sensor nodes. In general, energy consumption will be a significant concern for WSN owing to irreplaceable battery constraints of sensor nodes. The zone formation approach could be an adequate data aggregation technique which efficiently minimizes the energy consumption by categorizing sensor nodes into zones. However, the main constraints like zone head (ZH) selection, frequent change of ZH, and multi-hop communication from ZH to the sink have a direct impact on the network consistency of WSN. In this paper, a novel efficient intra- and inter-zone routing scheme has been proposed in order to prolong the network consistency of WSN. In the proposed scheme, the hybrid algorithm is established in which harmony search algorithm incorporates with modified moth flame optimization algorithm. This hybrid algorithm provides the appropriate ZH selection for intra-zone routing that reduces the frequent change of ZH in the network. Furthermore, the path balancing in inter-zone routing is acquired through multi-criteria-based optimal path routing algorithm. The performance results confirm that the proposed scheme enhances the network consistency compared with an existing scheme.