Enhancing wireless sensor network security and efficiency with CNN-FL and NGO optimization M. Shanmathi, Abhilash Sonker, Zair Hussain, Mohd Ashraf, Mangal Singh, Maganti Syamala Measurement Sensors, 2024 In this study, we discuss how Wireless Sensor Networks (WSN) are susceptible to malicious assaults from malfunctioning nodes, which jeopardise the security of data transmission in crucial applications. We use a Convolutional Neural Network coupled with Fuzzy Logic (CNN-FL) for improved deep learning, introducing a unique method, effectively identifying and categorizing trustworthy and malicious nodes. This is combined with a routing strategy enhanced by the Neuro Genetic Optimizer (NGO), built on the LEACH routing protocol and based on a Roulette wheel selection mechanism. The WSN's lifetime is increased by our suggested routing method, which not only provides safe data transmission but also dramatically reduces latency and energy consumption. Simulation findings show that our technique outperforms current protocols as ASNGSRA, DMCNN, and FRCSROD in terms of packet delivery ratio, energy economy, and latency analysis.
A new procedure for misbehavior detection in vehicular ad-hoc networks using machine learning Abhilash Sonker, R. K. Gupta International Journal of Electrical and Computer Engineering, 2021 Misbehavior detection in vehicular ad hoc networks (VANETs) is performed to improve the traffic safety and driving accuracy. All the nodes in the VANETs communicate to each other through message logs. Malicious nodes in the VANETs can cause inevitable situation by sending message logs with tampered values. In this work, various machine learning algorithms are used to detect the primarily five types of attacks namely, constant attack, constant offset attack, random attack, random offset attack, and eventual attack. Firstly, each attack is detected by different machine learning algorithms using binary classification. Then, the new procedure is created to do the multi classification of the attacks on best chosen algorithm from different machine learning techniques. The highest accuracy in case of binary classification is obtained with Naïve Bayes (100%), decision tree (100%), and random forest (100%) in type1 attack, decision tree (100%) in type2 attack, and random forest (98.03%, 95.56%, and 95.55%) in Type4, Type8 and Type16 attack respectively. In case of new procedure for multi-classification, the highest accuracy is obtained with random forest (97.62%) technique. For this work, VeReMi dataset (a public repository for the malicious node detection in VANETs) is used.
Application of hyperparameter optimized deep learning neural network for classification of air quality data International Journal of Scientific and Technology Research, 2019
Benefaction of Digital Image Processing Techniques in Quality Assessment of Rose Flower Anuradha Sharma, Abhilash Sonker 2019 10th International Conference on Computing Communication and Networking Technologies Icccnt 2019, 2019 Plants shows crucial significance being a part in an ecological community as they maintain the atmosphere. It is back breaking to scan the flower quality by hands. It has requirement of extensive work and also it needs of huge quantity of processing time. Therefore, DIP (digital image processing) is applicable in uncovering of flower quality detection. Recognition/detection of quality includes the steps like Image Acquisition(IA), Image Pre-processing(IPP), Image Segmentation(IS), Feature Extraction(FE) and its grouping. The motive of paper is to present a roadmap on the Detection of defected and non-defected(healthy) rose flower utilizing DIP (Digital Image Processing Methods). This will help research scholars to understand computer vision applications in quality assessment of Flowers.
