Niloy Sikder

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



Research Interests: Computational Learning Theory, Computer Architecture and Organization, Data Structures and Algorithms


Niloy Sikder is currently working as a research assistant at the Faculty of Technology and Bionics at Rhine-Waal University of Applied Sciences, Kleve, Germany, and as a PhD student at the Donders Center for Cognitive Neuroimaging (DCCN) at Radboud University, Nijmegen, The Netherlands. He received his BSc in Electronics and Communication Engineering (ECE) in 2017 and MSc in Computer Science and Engineering (CSE) in 2020 from Khulna University, Khulna, Bangladesh. His present research work at the Donders Sleep & Memory Lab is focused on investigating big sleep datasets with biomedical data processing and machine learning strategies.

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:, 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.
Other Articles