Files in this item

FilesDescriptionFormat

application/pdf

application/pdfSEO-DISSERTATION-2019.pdf (1MB)
(no description provided)PDF

Description

Title:Information-theoretic analysis of human-machine mixed systems
Author(s):Seo, Daewon
Director of Research:Varshney, Lav R.
Doctoral Committee Chair(s):Varshney, Lav R.
Doctoral Committee Member(s):Moulin, Pierre; Srikant, Rayadurgam; Veeravalli, Venugopal V.
Department / Program:Electrical & Computer Eng
Discipline:Electrical & Computer Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:Ph.D.
Genre:Dissertation
Subject(s):information theory, human-machine systems
Abstract:Many recent information technologies such as crowdsourcing and social decision-making systems are designed based on (near-)optimal information processing techniques for machines. However, in such applications, some parts of systems that process information are humans and so systems are affected by bounded rationality of human behavior and overall performance is suboptimal. In this dissertation, we consider systems that include humans and study their information-theoretic limits. We investigate four problems in this direction and show fundamental limits in terms of capacity, Bayes risk, and rate-distortion. A system with queue-length-dependent service quality, motivated by crowdsourcing platforms, is investigated. Since human service quality changes depending on workload, a job designer must take the level of work into account. We model the workload using queueing theory and characterize Shannon's information capacity for single-user and multiuser systems. We also investigate social learning as sequential binary hypothesis testing. We find somewhat counterintuitively that unlike basic binary hypothesis testing, the decision threshold determined by the true prior probability is no longer optimal and biased perception of the true prior could outperform the unbiased perception system. The fact that the optimal belief curve resembles the Prelec weighting function from cumulative prospect theory gives insight, in the era of artificial intelligence (AI), into how to design machine AI that supports a human decision. The traditional CEO problem well models a collaborative decision-making problem. We extend the CEO problem to two continuous alphabet settings with general rth power of difference and logarithmic distortions, and study matching asymptotics of distortion as the number of agents and sum rate grow without bound.
Issue Date:2019-06-05
Type:Text
URI:http://hdl.handle.net/2142/105592
Rights Information:Copyright 2019 Daewon Seo
Date Available in IDEALS:2019-11-26
Date Deposited:2019-08


This item appears in the following Collection(s)

Item Statistics