Enhance data availability and network consistency using artificial neural network for IoT

Tabassum, Mujahid; Perumal, Sundresan; Kashem, Saad Bin Abdul; Ponnan, Suresh; Chakraborty, Chinmay; Chowdhury, Muhammad E. H.; Khandakar, Amith

doi:10.1007/s11042-022-13337-6

Cited by 6 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To pick the group head, a half-and-half choice tree and counterfeit brain network technique are worked with mental radio [16]. As the remaining energy level rises, the base station accepts more packets and collects more data from typical sensor nodes.…”

Section: Literature Surveymentioning

confidence: 99%

Predicting and Recovering Link Failure Localization Using Competitive Swarm Optimization for DSR Protocol in MANET

R.,

Mohan,

Mahesh

2023

IJRITCC

View full text Add to dashboard Cite

Portable impromptu organization is a self-putting together, major construction-less, independent remote versatile hub that exists without even a trace of a determined base station or government association. MANET requires no extraordinary foundation as the organization is unique. Multicasting is an urgent issue in correspondence organizations. Multicast is one of the effective methods in MANET. In multicasting, information parcels from one hub are communicated to a bunch of recipient hubs all at once, at a similar time. In this research work, Failure Node Detection and Efficient Node Localization in a MANET situation are proposed. Localization in MANET is a main area that attracts significant research interest. Localization is a method to determine the nodes’ location in the communication network. A novel routing algorithm, which is used for Predicting and Recovering Link Failure Localization using a Genetic Algorithm with Competitive Swarm Optimization (PRLFL-GACSO) Algorithm is proposed in this study to calculate and recover link failure in MANET. The process of link failure detection is accomplished using mathematical modelling of the genetic algorithm and the routing is attained using the Competitive Swarm optimization technique. The result proposed MANET method makes use of the CSO algorithm, which facilitates a well-organized packet transfer from the source node to the destination node and enhances DSR routing performance. Based on node movement, link value, and endwise delay, the optimal route is found. The main benefit of the PRLFL-GACSO Algorithm is it achieves multiple optimal solutions over global information. Further, premature convergence is avoided using Competitive Swarm Optimization (CSO). The suggested work is measured based on the Ns simulator. The presentation metrix are PDR, endwise delay, power consumption, hit ratio, etc. The presentation of the proposed method is almost 4% and 5% greater than the present TEA-MDRP, RSTA-AOMDV, and RMQS-ua methods. After, the suggested method attains greater performance for detecting and recovering link failure. In future work, the hybrid multiway routing protocols are presented to provide link failure and route breakages and liability tolerance at the time of node failure, and it also increases the worth of service aspects, respectively.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Predicting and Recovering Link Failure Localization Using Competitive Swarm Optimization for DSR Protocol in MANET

R.,

Mohan,

Mahesh

2023

IJRITCC

View full text Add to dashboard Cite

show abstract

“…The algorithm with a novel probabilistic decision rule that was inspired by nature is proposed and serves as a fitness function to choose the best path for data transfer. To choose the cluster head, a hybrid artificial neural network and decision tree method were built with the cognitive radio [35]. The base station receives more packets and collects more data from the typical sensor nodes as the residual energy level rises.…”

Section: Related Workmentioning

confidence: 99%

Traffic-Aware Secured Cooperative Framework for IoT-Based Smart Monitoring in Precision Agriculture

Abunadi

Khan

Haseeb

et al. 2022

Sensors

View full text Add to dashboard Cite

In recent decades, networked smart devices and cutting-edge technology have been exploited in many applications for the improvement of agriculture. The deployment of smart sensors and intelligent farming techniques supports real-time information gathering for the agriculture sector and decreases the burden on farmers. Many solutions have been presented to automate the agriculture system using IoT networks; however, the identification of redundant data traffic is one of the most significant research problems. Additionally, farmers do not obtain the information they need in time, such as data on water pressure and soil conditions. Thus, these solutions consequently reduce the production rates and increase costs for farmers. Moreover, controlling all agricultural operations in a controlled manner should also be considered in developing intelligent solutions. Therefore, this study proposes a framework for a system that combines fog computing with smart farming and effectively controls network traffic. Firstly, the proposed framework efficiently monitors redundant information and avoids the inefficient use of communication bandwidth. It also controls the number of re-transmissions in the case of malicious actions and efficiently utilizes the network’s resources. Second, a trustworthy chain is built between agricultural sensors by utilizing the fog nodes to address security issues and increase reliability by preventing malicious communication. Through extensive simulation-based experiments, the proposed framework revealed an improved performance for energy efficiency, security, and network connectivity in comparison to other related works.

show abstract

“…optimization can maximize DNN performance; and (4) DNN models that execute many tasks outperform those that perform a single task. 29,30 Mayr et al 31 found that multitask DNN models won the Tox21 challenge on a dataset of 12,000 compounds for 12 high throughput toxicity experiments. Training of the model was done in parallel on GPU processors, the same as Dahl's design.…”

Section: Literature Reviewmentioning

confidence: 99%

(Retracted) DeepFNN-DTBA: prediction of drug-target binding affinity via feed-forward neural network on drug-protein sequences

Sharma

Deswal

2022

J. Electron. Imag.

View full text Add to dashboard Cite

The Editor-in-Chief and the publisher have retracted this article, which was submitted as part of a guest-edited special section. An investigation uncovered evidence of compromised peer review and determined the paper is out of the scope of the journal. The Editor and publisher no longer have confidence in the results and conclusions of the article.MS disagrees with the retraction. SD either did not respond or could not be reached.

show abstract

Enhance data availability and network consistency using artificial neural network for IoT

Cited by 6 publications

References 28 publications

Predicting and Recovering Link Failure Localization Using Competitive Swarm Optimization for DSR Protocol in MANET

Predicting and Recovering Link Failure Localization Using Competitive Swarm Optimization for DSR Protocol in MANET

Traffic-Aware Secured Cooperative Framework for IoT-Based Smart Monitoring in Precision Agriculture

(Retracted) DeepFNN-DTBA: prediction of drug-target binding affinity via feed-forward neural network on drug-protein sequences

Contact Info

Product

Resources

About