Rafia Nishat Toma

Work place: Electronics and Communication Engineering, KhulnaUniversity, Khulna-9208, Bangladesh

E-mail: rafiatoma@ece.ku.ac.bd


Research Interests: Microwave Measurements, Antenna Technology, Microwave Technology


Rafia Nishat Toma has completed her B.Sc. in Electronics and Communication Engineering from Khulna University, Khulna, Bangladesh in October 2012 and M.Sc. in the same discipline in June 2016. At present is working as Assistant Professor in Electronics and Communication Engineering Discipline at Khulna University. Her research interests include Microwave Antennas and propagation, design of Micro-stripe patch antenna.

Author Articles
Home Occupancy Classification Using Machine Learning Techniques along with Feature Selection

By Abdullah-Al Nahid Niloy Sikder Mahmudul Hasan Abid Rafia Nishat Toma Iffat Ara Talin Lasker Ershad Ali

DOI: https://doi.org/10.5815/ijem.2022.03.04, Pub. Date: 8 Jun. 2022

Monitoring systems for electrical appliances have gained massive popularity nowadays. These frameworks can provide consumers with helpful information for energy consumption. Non-intrusive load monitoring (NILM) is the most common method for monitoring a household’s energy profile. This research presents an optimized approach for identifying load needs and improving the identification of NILM occupancy surveillance. Our study suggested implementing a dimensionality reduction algorithm, popularly known as genetic algorithm (GA) along with XGBoost, for optimized occupancy monitoring. This exclusive model can masterly anticipate the usage of appliances with a significantly reduced number of voltage-current characteristics. The proposed NILM approach pre-processed the collected data and validated the anticipation performance by comparing the outcomes with the raw dataset’s performance metrics. While reducing dimensionality from 480 to 238 features, our GA-based NILM approach accomplished the same performance score in terms of accuracy (73%), recall (81%), ROC-AUC Score (0.81), and PR-AUC Score (0.81) like the original dataset. This study demonstrates that introducing GA in NILM techniques can contribute remarkably to reduce computational complexity without compromising performance.

[...] Read more.
Analysis the effect of Changing Height of the Substrate of Square Shaped Microstrip Patch Antenna on the Performance for 5G Application

By Rafia Nishat Toma Imtiaj Ahmmed Shohagh Md Nazmul Hasan

DOI: https://doi.org/10.5815/ijwmt.2019.03.04, Pub. Date: 8 May 2019

This paper deals with the design and study of parameters of square shaped microstrip patch antenna suitable for 5G communication systems. It is designed on Rogers RT Duroid 5880, which has a dielectric constant of 2.2. In this study, a micro-strip line fed patch antenna array, operating at a resonant frequency of 10.21GHz which is preferred for 5G applications, is implemented using the Computer Simulation Technology (CST) software. The designed antenna attained a fractional bandwidth of 1.62%, a wide bandwidth of 165 MHz and a reflection coefficient of -14.341dB. The transmission line used for the antenna is an inset feed. In order to design a microstrip patch antenna, the substrate material and its thickness are initially selected. The selection of a proper dielectric material and its thickness is very crucial in designing microstrip patch antenna. This paper also explains how antenna performance changes with the thickness variation of the substrate. The modified antennas can operate around 28 GHz and 10 GHz, the frequency bands recently proposed for 5G applications. The radiation pattern, return loss, 3D gain and VSWR curves are simulated for all designed antennas.

[...] Read more.
Other Articles