dc.contributor.advisor | Pasquier, Michel | |
dc.contributor.advisor | Hallal, Hicham | |
dc.contributor.author | Khan, Raviha W. | |
dc.date.accessioned | 2021-09-22T09:38:31Z | |
dc.date.available | 2021-09-22T09:38:31Z | |
dc.date.issued | 2021-08 | |
dc.identifier.other | 35.232-2021.29 | |
dc.identifier.uri | http://hdl.handle.net/11073/21544 | |
dc.description | A Master of Science thesis in Computer Engineering by Raviha W. Khan entitled, “An Intelligent System Approach for RF Energy Harvesting”, submitted in August 2021. Thesis advisor is Dr. Michel Bernard Pasquier and thesis co-advisor id Dr. Hicham Hallal. Soft copy is available (Thesis, Completion Certificate, Approval Signatures, and AUS Archives Consent Form). | en_US |
dc.description.abstract | RF energy harvesting has emerged as a viable energy source for low-powered devices in wireless sensor networks. It also acts as a replacement for conventional power sources such as batteries. RF energy harvest uses an unlimited source and makes efficient use of the existing energy in the surrounding environment. The use of machine learning techniques to predict the suitability of RF energy harvest under specific conditions further enhances the performance of energy harvesters. Such a prediction depends on several parameters, such as the time of the day, the temperature, the distance from source, the water density in the air, etc. These have a direct effect on the quality of the received signal at the harvesting node and thus, the harvested energy. In this thesis, a simulation of an RF energy harvesting network using MATLAB to collect relevant data is proposed. This data is used to train different machine learning models: Logistic Regression, Classification Trees, Support Vector Machines and Naïve Bayes in RStudio. The outcomes of the machine learning models are used to enhance the energy harvesting modules’ performance by scheduling them to be on or off with a given set of parametric values. The most suitable model for the dataset being used is chosen based on accuracy, F-Measure and Area Under the Curve. All the models evaluated in this thesis show a performance of 95% and above when tested. | en_US |
dc.description.sponsorship | College of Engineering | en_US |
dc.description.sponsorship | Department of Computer Science and Engineering | en_US |
dc.language.iso | en_US | en_US |
dc.relation.ispartofseries | Master of Science in Computer Engineering (MSCoE) | en_US |
dc.subject | RF Energy Harvesting | en_US |
dc.subject | Wireless Sensor Nodes | en_US |
dc.subject | Machine Learning | en_US |
dc.title | An Intelligent System Approach for RF Energy Harvesting | en_US |
dc.type | Thesis | en_US |