Matching Items (16)
Filtering by
- All Subjects: Computer Science
- Status: Published
Description
Splicing of digital images is a powerful form of tampering which transports regions of an image to create a composite image. When used as an artistic tool, this practice is harmless but when these composite images can be used to create political associations or are submitted as evidence in the judicial system they become more impactful. In these cases, distinction between an authentic image and a tampered image can become important.
Many proposed approaches to image splicing detection follow the model of extracting features from an authentic and tampered dataset and then classifying them using machine learning with the goal of optimizing classification accuracy. This thesis approaches splicing detection from a slightly different perspective by choosing a modern splicing detection framework and examining a variety of preprocessing techniques along with their effect on classification accuracy. Preprocessing techniques explored include Joint Picture Experts Group (JPEG) file type block line blurring, image level blurring, and image level sharpening. Attention is also paid to preprocessing images adaptively based on the amount of higher frequency content they contain.
This thesis also recognizes an identified problem with using a popular tampering evaluation dataset where a mismatch in the number of JPEG processing iterations between the authentic and tampered set creates an unfair statistical bias, leading to higher detection rates. Many modern approaches do not acknowledge this issue but this thesis applies a quality factor equalization technique to reduce this bias. Additionally, this thesis artificially inserts a mismatch in JPEG processing iterations by varying amounts to determine its effect on detection rates.
Many proposed approaches to image splicing detection follow the model of extracting features from an authentic and tampered dataset and then classifying them using machine learning with the goal of optimizing classification accuracy. This thesis approaches splicing detection from a slightly different perspective by choosing a modern splicing detection framework and examining a variety of preprocessing techniques along with their effect on classification accuracy. Preprocessing techniques explored include Joint Picture Experts Group (JPEG) file type block line blurring, image level blurring, and image level sharpening. Attention is also paid to preprocessing images adaptively based on the amount of higher frequency content they contain.
This thesis also recognizes an identified problem with using a popular tampering evaluation dataset where a mismatch in the number of JPEG processing iterations between the authentic and tampered set creates an unfair statistical bias, leading to higher detection rates. Many modern approaches do not acknowledge this issue but this thesis applies a quality factor equalization technique to reduce this bias. Additionally, this thesis artificially inserts a mismatch in JPEG processing iterations by varying amounts to determine its effect on detection rates.
ContributorsGubrud, Aaron (Author) / Li, Baoxin (Thesis advisor) / Candan, Kasim (Committee member) / Kadi, Zafer (Committee member) / Arizona State University (Publisher)
Created2015
Description
A common challenge faced by students is that they often have questions about course material that they cannot ask during lecture time. There are many ways for students to have these questions answered, such as office hours and online discussion boards. However, office hours may be at inconvenient times or locations, and online discussion boards are difficult to navigate and may be inactive. The purpose of this project was to create an Alexa skill that allows users to ask their Alexa-equipped device a question concerning their course material and to receive an answer retrieved from discussion board data. User questions are mapped to discussion board posts by use of the cosine similarity algorithm. In this algorithm, posts from the discussion board and the user’s question are converted into mathematical vectors, with each term in the vector corresponding to a word. The values of these terms are computed based on the word’s frequency within the vector’s corresponding document, the frequency of that word within all the documents, and the length of the document. After the question and candidate posts are converted into vectors, the algorithm determines the post most similar to the user’s question by computing the angle between the vectors. With the most similar discussion board post determined, the user receives the replies to the post, if any, as their answer. Users are able to indicate to their Alexa device whether they were satisfied by the answer, and if they were unsatisfied then they are given the opportunity to either rephrase their question or to have the question sent to a database of unanswered questions. The professor can view and answer the questions in this database on a website hosted by use of Amazon’s Simple Storage Service. The Alexa skill does well at answering questions that have already been asked in the discussion board. However, the skill depends heavily on the user’s word choice. Two questions that are semantically identical but different in phrasing are often given different answers. This is because the cosine algorithm measures similarity on the basis of word overlap, not semantic meaning, and thus the application never truly “understands” what type of answer the user desires. Improving the performance of this Alexa skill will require a more advanced question answering algorithm, but the limitations of Amazon Web Services as a development platform make implementing such an algorithm difficult. Nevertheless, this project has created the basis of a question answering Alexa skill by demonstrating a feasible way that the resources offered by Amazon can be utilized in order to build such an application.
ContributorsBaker, Matthew Elias (Author) / Chen, Yinong (Thesis director) / Balasooriya, Janaka (Committee member) / Historical, Philosophical & Religious Studies (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
Charleston, South Carolina currently faces serious annual flooding issues due to tides and rainfall. These issues are expected to get significantly worse within the next few decades reaching a projected 180 days a year of flooding by 2045 (Carter et al., 2018). Several permanent solutions are in progress by the City of Charleston. However, these solutions are years away at minimum and faced with development issues. This thesis attempts to treat some of the symptoms of flooding, such as navigation, by creating an iPhone application which predicts flooding and helps people navigate around it safely. Specifically, this thesis will take into account rainfall and tide levels to display to users actively flooded areas of downtown Charleston and provide routing to a destination from a user’s location around these flooded areas whenever possible.
ContributorsSalisbury, Mason (Author) / Balasooriya, Janaka (Thesis director) / Faucon, Christophe (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
Since the release of Discord in March of 2015 it has become the choice VoIP client for 25 million users, pulling in more each day from many sources including online video games with no voice chat, such as League of Legends. With such an expansive user base and many servers hosting multiple users during all times of the day, for a server admin to always be monitoring users is unreasonable. AhriBot aims to solve this problem by providing general administration through a command system to a server while it is logged onto that server. Specifically, AhriBot will be tailored for use on servers where League of Legends is primarily being played. Using commands issued to AhriBot, users can get statistics about their current game. By providing a set of features for general users, and a more specific set of features for League of Legends, AhriBot provides a greater experience and will help players to have quicker access to information about the game without having to travel to multiple outside sources.
ContributorsKoehler, Brendan Joseph (Author) / Balasooriya, Janaka (Thesis director) / Faucon, Philippe (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2017-12
Description
When scientific software is written to specify processes, it takes the form of a workflow, and is often written in an ad-hoc manner in a dynamic programming language. There is a proliferation of legacy workflows implemented by non-expert programmers due to the accessibility of dynamic languages. Unfortunately, ad-hoc workflows lack a structured description as provided by specialized management systems, making ad-hoc workflow maintenance and reuse difficult, and motivating the need for analysis methods. The analysis of ad-hoc workflows using compiler techniques does not address dynamic languages - a program has so few constrains that its behavior cannot be predicted. In contrast, workflow provenance tracking has had success using run-time techniques to record data. The aim of this work is to develop a new analysis method for extracting workflow structure at run-time, thus avoiding issues with dynamics.
The method captures the dataflow of an ad-hoc workflow through its execution and abstracts it with a process for simplifying repetition. An instrumentation system first processes the workflow to produce an instrumented version, capable of logging events, which is then executed on an input to produce a trace. The trace undergoes dataflow construction to produce a provenance graph. The dataflow is examined for equivalent regions, which are collected into a single unit. The workflow is thus characterized in terms of its treatment of an input. Unlike other methods, a run-time approach characterizes the workflow's actual behavior; including elements which static analysis cannot predict (for example, code dynamically evaluated based on input parameters). This also enables the characterization of dataflow through external tools.
The contributions of this work are: a run-time method for recording a provenance graph from an ad-hoc Python workflow, and a method to analyze the structure of a workflow from provenance. Methods are implemented in Python and are demonstrated on real world Python workflows. These contributions enable users to derive graph structure from workflows. Empowered by a graphical view, users can better understand a legacy workflow. This makes the wealth of legacy ad-hoc workflows accessible, enabling workflow reuse instead of investing time and resources into creating a workflow.
The method captures the dataflow of an ad-hoc workflow through its execution and abstracts it with a process for simplifying repetition. An instrumentation system first processes the workflow to produce an instrumented version, capable of logging events, which is then executed on an input to produce a trace. The trace undergoes dataflow construction to produce a provenance graph. The dataflow is examined for equivalent regions, which are collected into a single unit. The workflow is thus characterized in terms of its treatment of an input. Unlike other methods, a run-time approach characterizes the workflow's actual behavior; including elements which static analysis cannot predict (for example, code dynamically evaluated based on input parameters). This also enables the characterization of dataflow through external tools.
The contributions of this work are: a run-time method for recording a provenance graph from an ad-hoc Python workflow, and a method to analyze the structure of a workflow from provenance. Methods are implemented in Python and are demonstrated on real world Python workflows. These contributions enable users to derive graph structure from workflows. Empowered by a graphical view, users can better understand a legacy workflow. This makes the wealth of legacy ad-hoc workflows accessible, enabling workflow reuse instead of investing time and resources into creating a workflow.
ContributorsAcűna, Ruben (Author) / Bazzi, Rida (Thesis advisor) / Lacroix, Zoé (Thesis advisor) / Candan, Kasim (Committee member) / Arizona State University (Publisher)
Created2015
Description
Bank institutions employ several marketing strategies to maximize new customer acquisition as well as current customer retention. Telemarketing is one such approach taken where individual customers are contacted by bank representatives with offers. These telemarketing strategies can be improved in combination with data mining techniques that allow predictability of customer information and interests. In this thesis, bank telemarketing data from a Portuguese banking institution were analyzed to determine predictability of several client demographic and financial attributes and find most contributing factors in each. Data were preprocessed to ensure quality, and then data mining models were generated for the attributes with logistic regression, support vector machine (SVM) and random forest using Orange as the data mining tool. Results were analyzed using precision, recall and F1 score.
ContributorsEjaz, Samira (Author) / Davulcu, Hasan (Thesis advisor) / Balasooriya, Janaka (Committee member) / Candan, Kasim (Committee member) / Arizona State University (Publisher)
Created2016
Description
Improving accessibility to public buildings by people with special needs has been an important societal commitment that is mandated by federal laws. In the information age, accessibility can mean more than simply providing physical accommodations like ramps for wheel-chairs. Better yet, accessibility will be fundamentally improved, if a user can be made aware of important location-specific information like functions of offices near the user within a building. A smart environment may help a new person quickly get acquainted about the environment. Such features can be more critical for cases of making an indoor environment more accessible to people with visual impairment. With the intention to promote the integration of visually impaired people in society, this thesis efforts on methodologies for building smart and accessible indoor office environments with the help of Apple's Bluetooth Low Energy (BLE) technology called iBeacon to provide location awareness and enable easy access to information about the environment to people with visual impairment. This thesis presents work done on developing an iterative based approach in improving the configuration of given number of iBeacons to gain optimal signal coverage in a given office space environment and enabling smart features such as tagging points of interest and push notifications. This work aims to exploit the idea to look at visual impairment beyond the level of disability and cash it at as an opportunity to bring about a change of style of living. This work develops a methodology by introducing an end-to-end systems that uses intelligent server side and visually-impaired-friendly client side interfaces to give a prototype of an assistive technology to help them do basic activities like getting familiarized about an office environment without the need for asking for assistance.
ContributorsLagisetty, Jashmi (Author) / Li, Baoxin (Thesis advisor) / Hedgpeth, Terri (Committee member) / Balasooriya, Janaka (Committee member) / Arizona State University (Publisher)
Created2017
Description
Service based software (SBS) systems are software systems consisting of services based on the service oriented architecture (SOA). Each service in SBS systems provides partial functionalities and collaborates with other services as workflows to provide the functionalities required by the systems. These services may be developed and/or owned by different entities and physically distributed across the Internet. Compared with traditional software system components which are usually specifically designed for the target systems and bound tightly, the interfaces of services and their communication protocols are standardized, which allow SBS systems to support late binding, provide better interoperability, better flexibility in dynamic business logics, and higher fault tolerance. The development process of SBS systems can be divided to three major phases: 1) SBS specification, 2) service discovery and matching, and 3) service composition and workflow execution. This dissertation focuses on the second phase, and presents a privacy preserving service discovery and ranking approach for multiple user QoS requirements. This approach helps service providers to register services and service users to search services through public, but untrusted service directories with the protection of their privacy against the service directories. The service directories can match the registered services with service requests, but do not learn any information about them. Our approach also enforces access control on services during the matching process, which prevents unauthorized users from discovering services. After the service directories match a set of services that satisfy the service users' functionality requirements, the service discovery approach presented in this dissertation further considers service users' QoS requirements in two steps. First, this approach optimizes services' QoS by making tradeoff among various QoS aspects with users' QoS requirements and preferences. Second, this approach ranks services based on how well they satisfy users' QoS requirements to help service users select the most suitable service to develop their SBSs.
ContributorsYin, Yin (Author) / Yau, Stephen S. (Thesis advisor) / Candan, Kasim (Committee member) / Dasgupta, Partha (Committee member) / Santanam, Raghu (Committee member) / Arizona State University (Publisher)
Created2011
ContributorsShah, Beejal (Author) / Nakamura, Mutsumi (Thesis director) / Balasooriya, Janaka (Committee member) / Wilkerson, Kelly (Committee member) / Ira A. Fulton School of Engineering (Contributor) / Barrett, The Honors College (Contributor)
Created2012-12
Description
It is important for organizations and businesses to have some kind of online presence, as there are enormous benefits, including utilizing the power of web languages to provide services for people. However, creating a website is difficult, and often expensive. While successful businesses can use their profits to develop a costly website, organizations are not so lucky and can't afford to pay large amounts of money for theirs. Thus, the goal of this project was to provide a complete website to the Card Trick Quilters organization found in Show Low, Arizona. The website serves as both a learning experience, to see exactly what it takes to construct a website from the ground up, and a service project that will provide the Card Trick Quilters with a website that performs various services for its members, with functionality that is completely unique to the Arizona quilting community at large. The creation of the website required learning several different skills in regards to web design, such as databases, scripting languages, and even elements of graphic design. The uniqueness of the website comes from the creation of an online submission form for the annual quilt show hosted by the quilters, and an email reminder system where members of the community can submit their addresses and receive emails when there is an upcoming meeting. While there will no doubt be changes and improvements to the website in the future, the website is currently live and ready for the community to use.
ContributorsSchwarting, Jessa Lynn (Author) / Balasooriya, Janaka (Thesis director) / Nakamura, Mutsumi (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor) / School of Computing, Informatics, and Decision Systems Engineering (Contributor)
Created2016-05