Transactions on Engineering and Computing Sciences

A Genetic Algorithm with a Trust Model Function for Detecting Sinkhole and Wormhole Nodes in Wireless Sensor Networks

Rafiw Seidu, Abdul-Mumin Selanwiah Salifu, Johnbosco A. K. Ansuura — Wed, 24 Jul 2024 00:00:00 +0100

This study delved into wireless sensor networks, comprising numerous nodes with limited energy, computation, and transmission capabilities. Wireless sensor networks face security challenges due to their vulnerability to capture and compromise in insecure environments. Malicious nodes exploit communication's wireless nature, engaging in sinkhole and wormhole attacks. To address this, we propose a genetic strategy utilising a trust-based formula as a fitness function to evaluate sensor node reliability. Nodes progressing beyond a trust threshold criterion are identified, isolating malicious nodes responsible for attacks. Implemented in MATLAB 2018a, our approach effectively identifies and isolates such nodes, as demonstrated by the results.

Vehicle Monitoring and Tracking System

Adnan Shaout, Hisham Gaber — Sat, 13 Jul 2024 00:00:00 +0100

In this paper we present a vehicle monitoring and tracking system. Previous systems focus solely on either theft detection or car/driver monitoring. In this paper we provide an integrated solution that provide both theft detection, tracking and driver behavior monitoring. Our system performs well in detecting theft attempts through RFID and tracking location by GPS. It also monitors the driver behavior using OBD reader. Combining both features in one system has great advantages like cost efficiency, space saving and the possibility of adding new features.

Machine Learning Based Hybrid State-of-Charge Estimation and Other Battery Parameter Prediction of Commercial EV-Batteries

Tarik Hawsawi, Mohamed Zohdy — Wed, 24 Jul 2024 00:00:00 +0100

Electrical Vehicles (EVs) are gaining huge attention from researchers due to their importance in environmental sustainability. Accurate and precise EV State-of-Charge (SoC) estimation is the primary challenge for commercial E V Batteries. To address the issue, the researchers have proposed many methods. However, there are a few drawbacks in the existing methods which can be resolved using hybridization of the variants of existing methods. In the previously reported work, the Kalman filter was used for the SoC estimation of EV batteries, which is suitable for linear systems. In most practical cases, the SoC of the EV-Batteries system shows nonlinear behavior. Although, there are many other methods, e.g., Extended Kalman and Modified Extended Kalman reported by the researchers but there are some other drawbacks with the existing methods. To resolve the issues, the multi-variable optimization approach can be used to improve the accuracy of the SoC. The present work uses the hybridization of machine learning method to predict and estimate the SoC for commercial EV batteries. Machine learning methods precisely tunes the parameters and optimizes the estimation process by iteratively searching for the optimal solution within a defined parameter space. The performance of the proposed method is analyzed using Jupyter Notebook Platform (Scikit Learn Library). The results prove the superiority of the proposed method.