Numerous network can be connected by using the mobile ad hoc network. It can have security attacks like the worm hole, denial of service attack, jellyfish and also the blackhole. During this they take a path which is the shortest for the place where it has to reach. During sending of message two types of attacks are generally seen such as the blackhole attack and the wormhole attack. In this research we have tried to focus on two major attacks such as the black hole and the worm hole attack. In this we have used two types of protocol such as the AODV whose other name is SWBAODV and the scalable-dynamic elliptic curve cryptography. During the use the prime numbers are selected at random. We can also choose certain specific prime number. Moreover the security level does not depend on the size of the key. Keeping A as worm hole and B as the black hole we have made a two dimensional vector function named as F [A, B]. Two types of study is done by us in our research such as the with attack and without attack. In case of no attack study we have shown graphically using the AODV and the in case of attack we have given it as the BAODV and also the WAODV. Here we have applied a specific method SWBAODV to our selected attack case. The results were found to be interesting for the case of, packet delivery ratio and end to end delay was near 188.40 on comparing it with the BAODV and the WAODV. It has shown 51.38% more value compared to the BAODV and WAODV. There has been a drastic fall in the value of delay and it reached to a 63.2 for BAODV to WAODV. The other two things which we have discussed here is the consumption of energy and the overhead routing. The results in case of SWBAODV were good compared with the consumption of energy and save about 73.52% with the attacked case and around 69.35% with the routing done on the BAODV and WAODV. From our study we were able to say that it will give protection to the (MANET).

A MANET is a decentralized type of wireless network of mobile devices, it can also be defined as an autonomous system of nodes. All the nodes in the network are connected by wireless links and are mobile. They can come together and form a network without any support from any existing network infrastructure. MANET is a new field of study based on blockchain in a wireless ad-hoc environment. However, the main challenge for blockchain applications in ad-hoc networks is how to adapt to the extreme computational complexity of block validation while preserving the characteristics of blockchain and include nodes in the validation process. This article proposes a blockchain-based mobile network (MANET) with an ensemble algorithm. The proposed scheme provides a distributed environment for MANETS routing using a blockchain based on the Byzantine Fault Tolerance (BFT) protocol. Taking advantage of the better approach of mobile ad-hoc networking (BATMAN) to incorporate the concept of blockchain into the MANET as a representative protocol. The proposed method named Extended-BATMAN (E-BATMAN) incorporates the concept of blockchain into BATMAN protocol using MANET. As a secure, distributed and reliable platform, Blockchain solves most BFT security issues, with each node performing repeated security operations individually. The experimental analysis of the proposed ensemble algorithm is based on four parameters such as packet delivery rate, average end-to-end latency, network throughput, and energy. All of these parameters show better results with the proposed ensemble protocol than with existing state-of-the-art protocols.

Image Incorporation concerns, including background confusion, uneven population distribution, and variations in scale and familiarity, can make group counting difficult. Pre-existing information and multi-level contextual representations are required to handle these problems effectively with deep neural networks and Mask-RCNN. Numerous studies on crowd counting use density maps without segmentation, which treat a group of individuals as a single entity. This article offers a hybrid method for crowd counting that combines Mask-RCNN (MRCNN) and a bidirectional convolutional long-term memory network (ConvLSTM), dubbed (CC: MRCNN-biCLSTM). The CC: MRCNN-biCLSTM is based on the Mask-RCN; it first segments instances and generates density maps, which are passed into adversarial learning during the training phase. Finally, the bidirectional convolutional LSTM is being used to return metrics and counts for individuals within a group of individuals. Following that, the suggested activity detection technique based on the Bayesian non-linear filter AD-BNF is used to identify a person’s activity. Additionally, the suggested approach resolves human grouping and enhances metric performance. Extensive studies demonstrate that the suggested method outperforms more sophisticated techniques on four frequently used difficult criteria for density map precision and quality.

No abstract

No abstract