Files in this item

FilesDescriptionFormat

application/pdf

application/pdfZHAO-THESIS-2019.pdf (7MB)Restricted Access
(no description provided)PDF

Description

Title:Smart building waste monitoring system based on unsupervised learning
Author(s):Zhao, Yiran
Advisor(s):Abdelzaher, Tarek F.
Department / Program:Computer Science
Discipline:Computer Science
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:M.S.
Genre:Thesis
Subject(s):Smart home
Vibration analysis
Waste management
Abstract:The proliferation of Internet-of-Things (IoT) devices and maturing machine learning technologies have spawn numerous smart services permeating in every day life. These cyber-physical systems are fundamentally changing the way of managing resources, analyzing data and interacting with the physical world. The concept of smart building is a rapidly developing vision that brings intelligence closer to human life. However, transforming the existing building management infrastructure to an intelligent one requires an expensive revamp, if not an overhaul, to the physical environment. This thesis focuses on developing affordable, incrementally deployable smart systems with an example on waste management. Indoor waste management is crucial to a healthy environment in smart buildings. Measuring the waste bin fill-level helps building operators schedule garbage collection more responsively and optimize the quantity and location of waste bins. Simple and direct solutions face many challenges. For example, intrusively measuring the physical quantities of the garbage (weight, height, volume, etc.) or its appearance (image), requires careful device installation, laborious human calibration or labeling, and is costly. Such design is not economically viable or incrementally deployable. This work presents a system called VibeBin, that indirectly measures fill-level by sensing the changes in motor-induced vibration characteristics on the outside surface of waste bins. VibeBin exploits the physical nature of vibration resonance of the waste bin and the garbage within, and learns the vibration features of different fill-levels through a few garbage collection (emptying) cycles in a completely unsupervised manner. The evaluation shows that accurate level measurements can be made within a short period of time, without any human effort involved in the process. Therefore, our design enjoys wide deployment potential which is aimed at optimizing smart building management.
Issue Date:2019-04-23
Type:Text
URI:http://hdl.handle.net/2142/105163
Rights Information:Copyright 2019 Yiran Zhao
Date Available in IDEALS:2019-08-23
Date Deposited:2019-05


This item appears in the following Collection(s)

Item Statistics