College of Computer Science and Engineering
Information & Computer Science Department
Presents Public Seminar
Edge computing in industry applications
Date: 10th February, 2021
Time: 03:30 pm – 4:15 pm
Location: MS Teams Link: Click here to join the meeting
Mr. Abdolmaged Alkhulaifi
Non-intrusive load monitoring (NILM) allows us to identify the power consumption of each individual home appliance from a single meter. Acquiring the appliance-level power consumption can guide household occupants to take effective action to reduce their electrical consumption. Transformer models shown to be a promising approach to capture the global context of the sequence in fewer parameters compared to CNN models. Following the success of the transformer model in computer vision tasks, we propose to use transformer model for NILM. The transformer model is lightweight and contains around 98% less parameters compared to the state-of-the-art models. We have applied our proposed transformer model on a real-world dataset and found that it performs on-par with state-of-the-art CNN models while being extremely lighter.
Mr. Alkhulaifi is currently a Master student in computer science. His research interests include Non-intrusive load monitoring (also known as energy disaggregation), knowledge distillation and continual learning.
All faculty, researchers and graduate students are invited to attend.
Information & Computer Science Department, College of Computer Sciences and Engineering
Telephone: +966 (13) 860 2175, Email: email@example.com, Website: www.kfupm.edu.sa/departments/ics/
Copyright © 2014 King Fahd University of Petroleum & Minerals