Matching Items (1,501)
Filtering by
- Creators: College of Liberal Arts and Sciences
- Creators: Computer Science and Engineering Program
- Resource Type: Text
Description
With the emergence of edge computing paradigm, many applications such as image recognition and augmented reality require to perform machine learning (ML) and artificial intelligence (AI) tasks on edge devices. Most AI and ML models are large and computational heavy, whereas edge devices are usually equipped with limited computational and storage resources. Such models can be compressed and reduced in order to be placed on edge devices, but they may loose their capability and may not generalize and perform well compared to large models. Recent works used knowledge transfer techniques to transfer information from a large network (termed teacher) to a small one (termed student) in order to improve the performance of the latter. This approach seems to be promising for learning on edge devices, but a thorough investigation on its effectiveness is lacking.
The purpose of this work is to provide an extensive study on the performance (both in terms of accuracy and convergence speed) of knowledge transfer, considering different student-teacher architectures, datasets and different techniques for transferring knowledge from teacher to student.
A good performance improvement is obtained by transferring knowledge from both the intermediate layers and last layer of the teacher to a shallower student. But other architectures and transfer techniques do not fare so well and some of them even lead to negative performance impact. For example, a smaller and shorter network, trained with knowledge transfer on Caltech 101 achieved a significant improvement of 7.36\% in the accuracy and converges 16 times faster compared to the same network trained without knowledge transfer. On the other hand, smaller network which is thinner than the teacher network performed worse with an accuracy drop of 9.48\% on Caltech 101, even with utilization of knowledge transfer.
The purpose of this work is to provide an extensive study on the performance (both in terms of accuracy and convergence speed) of knowledge transfer, considering different student-teacher architectures, datasets and different techniques for transferring knowledge from teacher to student.
A good performance improvement is obtained by transferring knowledge from both the intermediate layers and last layer of the teacher to a shallower student. But other architectures and transfer techniques do not fare so well and some of them even lead to negative performance impact. For example, a smaller and shorter network, trained with knowledge transfer on Caltech 101 achieved a significant improvement of 7.36\% in the accuracy and converges 16 times faster compared to the same network trained without knowledge transfer. On the other hand, smaller network which is thinner than the teacher network performed worse with an accuracy drop of 9.48\% on Caltech 101, even with utilization of knowledge transfer.
ContributorsSistla, Ragini (Author) / Zhao, Ming (Thesis advisor, Committee member) / Li, Baoxin (Committee member) / Tong, Hanghang (Committee member) / Arizona State University (Publisher)
Created2018
Description
Recent trends in big data storage systems show a shift from disk centric models to memory centric models. The primary challenges faced by these systems are speed, scalability, and fault tolerance. It is interesting to investigate the performance of these two models with respect to some big data applications. This thesis studies the performance of Ceph (a disk centric model) and Alluxio (a memory centric model) and evaluates whether a hybrid model provides any performance benefits with respect to big data applications. To this end, an application TechTalk is created that uses Ceph to store data and Alluxio to perform data analytics. The functionalities of the application include offline lecture storage, live recording of classes, content analysis and reference generation. The knowledge base of videos is constructed by analyzing the offline data using machine learning techniques. This training dataset provides knowledge to construct the index of an online stream. The indexed metadata enables the students to search, view and access the relevant content. The performance of the application is benchmarked in different use cases to demonstrate the benefits of the hybrid model.
ContributorsNAGENDRA, SHILPA (Author) / Huang, Dijiang (Thesis advisor) / Zhao, Ming (Committee member) / Maciejewski, Ross (Committee member) / Chung, Chun-Jen (Committee member) / Arizona State University (Publisher)
Created2017
Description
Compartmentalizing access to content, be it websites accessed in a browser or documents and applications accessed outside the browser, is an established method for protecting information integrity [12, 19, 21, 60]. Compartmentalization solutions change the user experience, introduce performance overhead and provide varying degrees of security. Striking a balance between usability and security is not an easy task. If the usability aspects are neglected or sacrificed in favor of more security, the resulting solution would have a hard time being adopted by end-users. The usability is affected by factors including (1) the generality of the solution in supporting various applications, (2) the type of changes required, (3) the performance overhead introduced by the solution, and (4) how much the user experience is preserved. The security is affected by factors including (1) the attack surface of the compartmentalization mechanism, and (2) the security decisions offloaded to the user. This dissertation evaluates existing solutions based on the above factors and presents two novel compartmentalization solutions that are arguably more practical than their existing counterparts.
The first solution, called FlexICon, is an attractive alternative in the design space of compartmentalization solutions on the desktop. FlexICon allows for the creation of a large number of containers with small memory footprint and low disk overhead. This is achieved by using lightweight virtualization based on Linux namespaces. FlexICon uses two mechanisms to reduce user mistakes: 1) a trusted file dialog for selecting files for opening and launching it in the appropriate containers, and 2) a secure URL redirection mechanism that detects the user’s intent and opens the URL in the proper container. FlexICon also provides a language to specify the access constraints that should be enforced by various containers.
The second solution called Auto-FBI, deals with web-based attacks by creating multiple instances of the browser and providing mechanisms for switching between the browser instances. The prototype implementation for Firefox and Chrome uses system call interposition to control the browser’s network access. Auto-FBI can be ported to other platforms easily due to simple design and the ubiquity of system call interposition methods on all major desktop platforms.
The first solution, called FlexICon, is an attractive alternative in the design space of compartmentalization solutions on the desktop. FlexICon allows for the creation of a large number of containers with small memory footprint and low disk overhead. This is achieved by using lightweight virtualization based on Linux namespaces. FlexICon uses two mechanisms to reduce user mistakes: 1) a trusted file dialog for selecting files for opening and launching it in the appropriate containers, and 2) a secure URL redirection mechanism that detects the user’s intent and opens the URL in the proper container. FlexICon also provides a language to specify the access constraints that should be enforced by various containers.
The second solution called Auto-FBI, deals with web-based attacks by creating multiple instances of the browser and providing mechanisms for switching between the browser instances. The prototype implementation for Firefox and Chrome uses system call interposition to control the browser’s network access. Auto-FBI can be ported to other platforms easily due to simple design and the ubiquity of system call interposition methods on all major desktop platforms.
ContributorsZohrevandi, Mohsen (Author) / Bazzi, Rida A (Thesis advisor) / Ahn, Gail-Joon (Committee member) / Doupe, Adam (Committee member) / Zhao, Ming (Committee member) / Arizona State University (Publisher)
Created2018
Description
The Internet of Things ecosystem has spawned a wide variety of embedded real-time systems that complicate the identification and resolution of bugs in software. The methods of concurrent checkpoint provide a means to monitor the application state with the ability to replay the execution on like hardware and software, without holding off and delaying the execution of application threads. In this thesis, it is accomplished by monitoring physical memory of the application using a soft-dirty page tracker and measuring the various types of overhead when employing concurrent checkpointing. The solution presented is an advancement of the Checkpoint and Replay In Userspace (CRIU) thereby eliminating the large stalls and parasitic operation for each successive checkpoint. Impact and performance is measured using the Parsec 3.0 Benchmark suite and 4.11.12-rt16+ Linux kernel on a MinnowBoard Turbot Quad-Core board.
ContributorsPrinke, Michael L (Author) / Lee, Yann-Hang (Thesis advisor) / Shrivastava, Aviral (Committee member) / Zhao, Ming (Committee member) / Arizona State University (Publisher)
Created2018
Description
Blockchain scalability is one of the issues that concerns its current adopters. The current popular blockchains have initially been designed with imperfections that in- troduce fundamental bottlenecks which limit their ability to have a higher throughput and a lower latency.
One of the major bottlenecks for existing blockchain technologies is fast block propagation. A faster block propagation enables a miner to reach a majority of the network within a time constraint and therefore leading to a lower orphan rate and better profitability. In order to attain a throughput that could compete with the current state of the art transaction processing, while also keeping the block intervals same as today, a 24.3 Gigabyte block will be required every 10 minutes with an average transaction size of 500 bytes, which translates to 48600000 transactions every 10 minutes or about 81000 transactions per second.
In order to synchronize such large blocks faster across the network while maintain- ing consensus by keeping the orphan rate below 50%, the thesis proposes to aggregate partial block data from multiple nodes using digital fountain codes. The advantages of using a fountain code is that all connected peers can send part of data in an encoded form. When the receiving peer has enough data, it then decodes the information to reconstruct the block. Along with them sending only part information, the data can be relayed over UDP, instead of TCP, improving upon the speed of propagation in the current blockchains. Fountain codes applied in this research are Raptor codes, which allow construction of infinite decoding symbols. The research, when applied to blockchains, increases success rate of block delivery on decode failures.
One of the major bottlenecks for existing blockchain technologies is fast block propagation. A faster block propagation enables a miner to reach a majority of the network within a time constraint and therefore leading to a lower orphan rate and better profitability. In order to attain a throughput that could compete with the current state of the art transaction processing, while also keeping the block intervals same as today, a 24.3 Gigabyte block will be required every 10 minutes with an average transaction size of 500 bytes, which translates to 48600000 transactions every 10 minutes or about 81000 transactions per second.
In order to synchronize such large blocks faster across the network while maintain- ing consensus by keeping the orphan rate below 50%, the thesis proposes to aggregate partial block data from multiple nodes using digital fountain codes. The advantages of using a fountain code is that all connected peers can send part of data in an encoded form. When the receiving peer has enough data, it then decodes the information to reconstruct the block. Along with them sending only part information, the data can be relayed over UDP, instead of TCP, improving upon the speed of propagation in the current blockchains. Fountain codes applied in this research are Raptor codes, which allow construction of infinite decoding symbols. The research, when applied to blockchains, increases success rate of block delivery on decode failures.
ContributorsChawla, Nakul (Author) / Boscovic, Dragan (Thesis advisor) / Candan, Kasim S (Thesis advisor) / Zhao, Ming (Committee member) / Arizona State University (Publisher)
Created2018
Description
The current trend of interconnected devices, or the internet of things (IOT) has led to the popularization of single board computers (SBC). This is primarily due to their form-factor and low price. This has led to unique networks of devices that can have unstable network connections and minimal processing power. Many parallel program- ming libraries are intended for use in high performance computing (HPC) clusters. Unlike the IOT environment described, HPC clusters will in general look to obtain very consistent network speeds and topologies. There are a significant number of software choices that make up what is referred to as the HPC stack or parallel processing stack. My thesis focused on building an HPC stack that would run on the SCB computer name the Raspberry Pi. The intention in making this Raspberry Pi cluster is to research performance of MPI implementations in an IOT environment, which had an impact on the design choices of the cluster. This thesis is a compilation of my research efforts in creating this cluster as well as an evaluation of the software that was chosen to create the parallel processing stack.
ContributorsO'Meara, Braedon Richard (Author) / Meuth, Ryan (Thesis director) / Dasgupta, Partha (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
This thesis discusses three recent optimization problems that seek to reduce disease spread on arbitrary graphs by deleting edges, and it discusses three approximation algorithms developed for these problems. Important definitions are presented including the Linear Threshold and Triggering Set models and the set function properties of submodularity and monotonicity. Also, important results regarding the Linear Threshold model and computation of the influence function are presented along with proof sketches. The three main problems are formally presented, and NP-hardness results along with proof sketches are presented where applicable. The first problem seeks to reduce spread of infection over the Linear Threshold process by making use of an efficient tree data structure. The second problem seeks to reduce the spread of infection over the Linear Threshold process while preserving the PageRank distribution of the input graph. The third problem seeks to minimize the spectral radius of the input graph. The algorithms designed for these problems are described in writing and with pseudocode, and their approximation bounds are stated along with time complexities. Discussion of these algorithms considers how these algorithms could see real-world use. Challenges and the ways in which these algorithms do or do not overcome them are noted. Two related works, one which presents an edge-deletion disease spread reduction problem over a deterministic threshold process and the other which considers a graph modification problem aimed at minimizing worst-case disease spread, are compared with the three main works to provide interesting perspectives. Furthermore, a new problem is proposed that could avoid some issues faced by the three main problems described, and directions for future work are suggested.
ContributorsStanton, Andrew Warren (Author) / Richa, Andrea (Thesis director) / Czygrinow, Andrzej (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
In the last few years, billion-dollar companies like Yahoo and Equifax have had data breaches causing millions of people’s personal information to be leaked online. Other billion-dollar companies like Google and Facebook have gotten in trouble for abusing people’s personal information for financial gain as well. In this new age of technology where everything is being digitalized and stored online, people all over the world are concerned about what is happening to their personal information and how they can trust it is being kept safe. This paper describes, first, the importance of protecting user data, second, one easy tool that companies and developers can use to help ensure that their user’s information (credit card information specifically) is kept safe, how to implement that tool, and finally, future work and research that needs to be done. The solution I propose is a software tool that will keep credit card data secured. It is only a small step towards achieving a completely secure data anonymized system, but when implemented correctly, it can reduce the risk of credit card data from being exposed to the public. The software tool is a script that can scan every viable file in any given system, server, or other file-structured Linux system and detect if there any visible credit card numbers that should be hidden.
ContributorsPappas, Alexander (Author) / Zhao, Ming (Thesis director) / Kuznetsov, Eugene (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
Political polarization is the coalescence of political parties -- and the individuals of which parties are composed -- around opposing ends of the ideological spectrum. Political parties in the United States have always been divided, however, in recent years this division has only intensified. Recently, polarization has also wound its way to the Supreme Court and the nomination processes of justices to the Court. This paper examines how prevalent polarization in the Supreme Court nomination process has become by looking specifically at the failed nomination of Judge Merrick Garland and the confirmations of now-Justices Neil Gorsuch and Brett Kavanaugh. This is accomplished by comparing the ideologies and qualifications of the three most recent nominees to those of previous nominees, as well as analysing the ideological composition of the Senate at the times of the individual nominations.
ContributorsJoss, Jacob (Author) / Hoekstra, Valerie (Thesis director) / Critchlow, Donald (Committee member) / Computer Science and Engineering Program (Contributor) / School of Politics and Global Studies (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
The original version of Helix, the one I pitched when first deciding to make a video game
for my thesis, is an action-platformer, with the intent of metroidvania-style progression
and an interconnected world map.
The current version of Helix is a turn based role-playing game, with the intent of roguelike
gameplay and a dark fantasy theme. We will first be exploring the challenges that came
with programming my own game - not quite from scratch, but also without a prebuilt
engine - then transition into game design and how Helix has evolved from its original form
to what we see today.
for my thesis, is an action-platformer, with the intent of metroidvania-style progression
and an interconnected world map.
The current version of Helix is a turn based role-playing game, with the intent of roguelike
gameplay and a dark fantasy theme. We will first be exploring the challenges that came
with programming my own game - not quite from scratch, but also without a prebuilt
engine - then transition into game design and how Helix has evolved from its original form
to what we see today.
ContributorsDiscipulo, Isaiah K (Author) / Meuth, Ryan (Thesis director) / Kobayashi, Yoshihiro (Committee member) / School of Mathematical and Statistical Sciences (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05