Computer Sciences Commons^™

Stay-At-Home Motor Rehabilitation: Optimizing Spatiotemporal Learning On Low-Cost Capacitive Sensor Arrays, Reid Sutherland

Graduate Theses and Dissertations

Repeated, consistent, and precise gesture performance is a key part of recovery for stroke and other motor-impaired patients. Close professional supervision to these exercises is also essential to ensure proper neuromotor repair, which consumes a large amount of medical resources. Gesture recognition systems are emerging as stay-at-home solutions to this problem, but the best solutions are expensive, and the inexpensive solutions are not universal enough to tackle patient-to-patient variability. While many methods have been studied and implemented, the gesture recognition system designer does not have a strategy to effectively predict the right method to fit the needs of a patient. …

Dynamics In Recommendations Of Updates For Free Open-Source Software, Shakre Elmane

Theses and Dissertations

In Free and Open-Source Software (FOSS) world, newer is not always better. Automatically updating to the latest version of FOSS applications involves real risks. The newer version could be missing features that are essential to some users, but are dropped by the developers. Another possible scenario, with even more serious consequences, is a project taken over by malicious developers who target users’ sensitive data, or try to control their systems. In this work we identify a set of security risks associated with changes of reviewers in automatic Free and Open-Source software (FOSS) updates. Automatic updates can be a prime target …

A Machine Learning Method For Predicting Liver Transplant Survival Outcomes, Brandon C. Revels

Honors Theses

For years, doctors have utilized the Model for End-stage Liver Disease (MELD) score to aid in the allocation of organs for liver transplants (LT). A major issue with using the MELD score to allocate organs for transplantation is that the MELD score does not accurately predict post-transplant survival. This research project aims to investigate the use of machine learning (ML) methods to predict LT survival using the newer Scientific Registry of Transplant Recipients (SRTR) dataset. For this project, death and nonfatal graft failure were treated equally as both cases result in a loss of a donated organ. The ML algorithms …

Meta-Analysis Of Biological Research Literature, Evan Suggs

Honors Theses

Comparative studies have been powerful tools in generating a broad understanding about the evolution of animal social systems but they currently rely on the slow, manual process of reading thousands of abstracts and papers from research databases. A web application was created for researchers conducting a comparative survey, in order to speed up their research. This web application automates the retrieval of research papers and their selection process. Using previously obtained data sets on the orders Artiodacytla and Lagomorph, a machine learning application was created to classify the papers. These techniques and tools should greatly increase the speed at which …

Vzwam Web-Based Lookup, Ruben Claudio

Masters Theses & Doctoral Dissertations

This web-based lookup will allow V employees to find territory sales rep much faster. It will simplify the process and eliminate manual processes.

At the moment, a combination of multiple manual processes is needed to find territory sales reps. The company’s CRM does not allow to find rep sales quickly. When an in-house sales representative is talking to a prospect, this sales rep has to go through a few series of steps to find an outside or territory sales rep --which is usually needed to schedule in-person meetings, that results in delays while doing transactions with the prospects. Besides, because …

Robotic Swarms: Assembly And Complexity, Angel Adrian Cantu Suarez

Theses and Dissertations

This thesis focuses on the assembly of robotic swarms that move according to some global signal in a model called the “tilt” model. The model consists of a 2D board that contain open and blocked spaces, along with tiles or polyominoes that move toward a signaled cardinal direction. We look at two variations of this model called the single-step and full-tilt model, where the elements move single distances or maximally, respectively, when a signal is send. We show different methods of shape construction, defining board configurations that are universal for a set of shapes. Afterwards, we analyze different computational problems …

Iclab: A Global, Longitudinal Internet Censorship Measurement Platform, Arian Akhavan Niaki, Shinyoung Cho, Zachary Weinberg, Nguyen Phong Hoang, Abbas Razaghpanah, Nicolas Christin, Phillipa Gill

Computer Science: Faculty Publications

Researchers have studied Internet censorship for nearly as long as attempts to censor contents have taken place. Most studies have however been limited to a short period of time and / or a few countries; the few exceptions have traded off detail for breadth of coverage. Collecting enough data for a comprehensive, global, longitudinal perspective remains challenging.In this work, we present ICLab, an Internet measurement platform specialized for censorship research. It achieves a new balance between breadth of coverage and detail of measurements, by using commercial VPNs as vantage points distributed around the world. ICLab has been operated continuously since …

Learning Abstractions For Planning, Brian Charles Cook

Computer Science and Engineering Dissertations - Archive

Planners for hard problems must exploit domain-specific structure to find solutions efficiently. Yet, hand-engineered solutions and optimizations are often expensive and difficult or impossible to adapt to other problems. This work applies automatic machine learning techniques to increase planner performance for specific problem domains and to learn useful abstract representations for planning. In particular, this dissertation develops methods to address important aspects of learning in planning in four different areas: State-of-the-art domain-independent classical planners utilize multiple search heuristics and decide how to allocate computational effort between heuristics prior to planning. This work presents a heuristic planning algorithm that uses a …

Predicting Disease Progression Using Deep Recurrent Neural Networks And Longitudinal Electronic Health Record Data, Seunghwan Kim

McKelvey School of Engineering Graduate Student Theses & Dissertations

Electronic Health Records (EHR) are widely adopted and used throughout healthcare systems and are able to collect and store longitudinal information data that can be used to describe patient phenotypes. From the underlying data structures used in the EHR, discrete data can be extracted and analyzed to improve patient care and outcomes via tasks such as risk stratification and prospective disease management. Temporality in EHR is innately present given the nature of these data, however, and traditional classification models are limited in this context by the cross-sectional nature of training and prediction processes. Finding temporal patterns in EHR is especially …

Fire Progression, Ashwini Badgujar, L. Zheng, S. Hu, Aj Purdy

Creative Activity and Research Day - CARD

Fires have grown up to 70% in recent years. Fire Progression is a Machine Learning research project wherein we are trying to predict the direction in which the fire might grow in future. We are using Machine Learning technique and features like surface temperature, air temperature, moisture, precipitation and other additional parameters to predict the progression.

Active/Transfer Learning With Medical Imaging, Nicholas Kebbas, Maggie Lu

Creative Activity and Research Day - CARD

We've developed a robust web application to assist researchers in improving the accuracy of their Machine Learning Models. The system provides an image labeling web interface so that researchers can label and classify the models, and multiple data visualizations that help researchers identify and resolve inconsistencies between the classifications determined by their models and user feedback.

Evaluation Of Visualization Techniques For Communicating Off-Screen Data, Tony Jimenez

Creative Activity and Research Day - CARD

Worldwide, the use of mobile devices like tablets has begun to integrate themselves in people’s daily lives. People have thus begun to bring over desktop applications, more specifically visualization applications, into the mobile atmosphere. However, this brings forth some challenges, like how to manage screen space and how the visualizations should present the relevant information. Our take on this was to use various aggregations that would allow users to see data elements that would otherwise be off-screen. We thought it was best to create a variety of different aggregations, allowing us to figure out the best method of the group. …

Practical Adversarial Attacks Against Black Box Speech Recognition Systems And Devices, Yuxuan Chen

Theses and Dissertations

With the advance of speech recognition technologies, intelligent voice control devices such as Amazon Echo have became increasingly popular in our daily life. Currently, most state-of-the-art speech recognition systems are using neural networks to further improve the accuracy and efficacy of the system. Unfortunately, neural networks are vulnerable to adversarial examples: inputs specifically designed by an adversary to cause a neural network to misclassify them. Hence, it becomes imperative to understand the security implications of the speech recognition systems in the presence of such attacks. In this dissertation, we first introduce an effective audio adversarial attack towards one white box …

Understanding Personal Data In The World Of Social Media, Nicholas Scott Rodgers

Undergraduate Honors Capstone Projects

Personal data is behind many of the online interactions that people have through social media and other online sites and services. This data allows sites to understand their users, which in turn allows them to provide better content for their users. This data is also used to determine user interests, which these online services use to target more relevant advertising to their users, and share the information that they collect about their users with third parties. It is only recently that this personal data is being regulated by lawmakers, the businesses running these sites are held accountable for managing the …

High Dimensional Event Exploration Over Multiple Simulations, Steven Deron Scott

Undergraduate Honors Capstone Projects

In this project, we introduce a visualization technique to analyze event simulation data. In particular, we allow the user to discover families of events based on the topological evolution of discrete events across simulations. Discovering how events behave across runs of a simulation has applications in financial market analysis, military simulations, physical mechanics, and other settings. Our approach is to use established methods to produce a linearized tour through parameter space of arbitrary dimension and visualize events of interest in two dimensions, where the first dimension is the tour ordering and the second dimension is usually time. This paper presents …

Predicting Disease Progression Using Deep Recurrent Neural Networks And Longitudinal Electronic Health Record Data, Seunghwan Kim

McKelvey School of Engineering Graduate Student Theses & Dissertations

Electronic Health Records (EHR) are widely adopted and used throughout healthcare systems and are able to collect and store longitudinal information data that can be used to describe patient phenotypes. From the underlying data structures used in the EHR, discrete data can be extracted and analyzed to improve patient care and outcomes via tasks such as risk stratification and prospective disease management. Temporality in EHR is innately present given the nature of these data, however, and traditional classification models are limited in this context by the cross- sectional nature of training and prediction processes. Finding temporal patterns in EHR is …

Characterization Of Written Text Using Data And Network Science, Harith A. Hamdon Hamoodat

Theses and Dissertations

The success of humans cannot be attributed to language, but it is certainly true that language and humans are inseparable. Since the first language appeared, we have seen that language continually evolving over space and social gatherings to formed around 7,000 languages today. The origin and evolution of languages still vague, and state-of-the-art in languages evolution still lack a comprehensive characterization. In general, this problem is mainly tackled by statistical measuring the changes on the part of the language ( e.g., words and sounds). Given the current availability of data and computational power, this dissertation proposes a comprehensive data-driven characterization …

Defense In Depth Of Resource-Constrained Devices, Ira Ray Jenkins

Dartmouth College Ph.D Dissertations

The emergent next generation of computing, the so-called Internet of Things (IoT), presents significant challenges to security, privacy, and trust. The devices commonly used in IoT scenarios are often resource-constrained with reduced computational strength, limited power consumption, and stringent availability requirements. Additionally, at least in the consumer arena, time-to-market is often prioritized at the expense of quality assurance and security. An initial lack of standards has compounded the problems arising from this rapid development. However, the explosive growth in the number and types of IoT devices has now created a multitude of competing standards and technology silos resulting in a …

Bridging The Gap Between Intent And Outcome: Knowledge, Tools & Principles For Security-Minded Decision-Making, Vijay Harshed Kothari

Dartmouth College Ph.D Dissertations

Well-intentioned decisions---even ones intended to improve aggregate security--- may inadvertently jeopardize security objectives. Adopting a stringent password composition policy ostensibly yields high-entropy passwords; however, such policies often drive users to reuse or write down passwords. Replacing URLs in emails with "safe" URLs that navigate through a gatekeeper service that vets them before granting user access may reduce user exposure to malware; however, it may backfire by reducing the user's ability to parse the URL or by giving the user a false sense of security if user expectations misalign with the security checks delivered by the vetting process. A short timeout …

A Mathematical Approach To Gomoku, Oscar Garcia

Theses and Dissertations

This goal of this thesis is to design and implement a light weighted AI for playing Gomoku with high level intelligence. Our work is built upon an innovative algebraic monomial theory to help assess values for each possible move and estimate chances for the AI to win at each move. With the help of the monomial theory, we are able to convert winning configurations into monomials of variables that represent the underlying board positions. In the existing approaches to building an AI for playing Gomoku, one common challenge is about how to represent the present configuration of the game along …

Algorithmic Assembly Of Nanoscale Structures, Austin Luchsinger

Theses and Dissertations

The development of nanotechnology has become one of the most significant endeavors of our time. A natural objective of this field is discovering how to engineer nanoscale structures. Limitations of current top-down techniques inspire investigation into bottom-up approaches to reach this objective. A fundamental precondition for a bottom-up approach is the ability to control the behavior of nanoscale particles. Many abstract representations have been developed to model systems of particles and to research methods for controlling their behavior. This thesis develops theories on two such approaches for building complex structures: the self-assembly of simple particles, and the use of simple …

Pmkt: Privacy-Preserving Multi-Party Knowledge Transfer For Financial Market Forecasting, Zhuoran Ma, Jianfeng Ma, Yinbin Miao, Kim-Kwang Raymond Choo, Ximeng Liu, Xiangyu Wang, Tengfei Yang

Research Collection School Of Computing and Information Systems

While decision-making task is critical in knowledge transfer, particularly from multi-source domains, existing knowledge transfer approaches are not generally designed to be privacy preserving. This has potential legal and financial implications, particularly in sensitive applications such as financial market forecasting. Therefore, in this paper, we propose a Privacy-preserving Multi-party Knowledge Transfer system (PMKT), based on decision trees, for financial market forecasting. Specifically, in PMKT, we leverage a cryptographic-based model sharing technique to securely outsource knowledge reflected in decision trees of multiple parties, and design a secure computation mechanism to facilitate privacy-preserving knowledge transfer. An encrypted user-submitted request from the target …

Memlock: Memory Usage Guided Fuzzing, Cheng Wen, Haijun Wang, Yuekang Li, Shengchao Qin, Yang Liu, Zhiwu Xu, Hongxu Chen, Xiaofei Xie, Geguang Pu, Ting Liu

Research Collection School Of Computing and Information Systems

Uncontrolled memory consumption is a kind of critical software security weaknesses. It can also become a security-critical vulnerability when attackers can take control of the input to consume a large amount of memory and launch a Denial-of-Service attack. However, detecting such vulnerability is challenging, as the state-of-the-art fuzzing techniques focus on the code coverage but not memory consumption. To this end, we propose a memory usage guided fuzzing technique, named MemLock, to generate the excessive memory consumption inputs and trigger uncontrolled memory consumption bugs. The fuzzing process is guided with memory consumption information so that our approach is general and …

Symbolic Verification Of Message Passing Interface Programs, Hengbiao Yu, Zhenbang Chen, Xianjin Fu, Ji Wang, Zhendong Su, Jun Sun, Chun Huang, Wei Dong

Research Collection School Of Computing and Information Systems

Message passing is the standard paradigm of programming in high-performance computing. However, verifying Message Passing Interface (MPI) programs is challenging, due to the complex program features (such as non-determinism and non-blocking operations). In this work, we present MPI symbolic verifier (MPI-SV), the first symbolic execution based tool for automatically verifying MPI programs with non-blocking operations. MPI-SV combines symbolic execution and model checking in a synergistic way to tackle the challenges in MPI program verification. The synergy improves the scalability and enlarges the scope of verifiable properties. We have implemented MPI-SV and evaluated it with 111 real-world MPI verification tasks. The …

Energy-Efficient Data Transmission With Clustering And Compressive Sensing In Wireless Sensor Networks, Alagirisamy Mukil

Student Works (2020-2029)

One of the most important application of wireless sensor network is environmental monitoring. The application involves lifetime of sensor nodes for longer duration associating its energy module. Wireless sensor nodes deployed in sensing field aggregate enormous amount of sensed data and transfer them to the sink. The inherent limitation of energy carried within the battery of sensor nodes fetches extreme difficulty to acquire adequate network lifetime, becoming a bottleneck in forwarding data to sink. Hence the motivation is to reduce the amount of data transfer and attain energy efficiency. This is achieved by clustering and compressive sensing techniques. First objective …

Supervised Optimal Decision Machine Learning Approach To Class- And Method-Level Data Preprocessing Towards Effective Software Defect Prediction, Felix Ebubeogu Amarachukwu

Student Works (2020-2029)

Software defect prediction provides actionable outputs to software teams while contributing to industrial success. Therefore, predicting the number of defects in a new version of software at both the class and method levels is an important goal of defect prediction studies to assist software teams in optimizing their test efforts towards improving software quality. However, despite remarkable achievements in defect prediction, the quality of the data applied in defect prediction studies has been a major concern, with related quality issues leading to numerous contradictory findings in machine learning research. In addition, a demonstrated approach for predicting the number of defects …

Partial Discharge Classification For Xlpe Cable Joints Using K Nearest Neighbors Algorithm, Mohd Salleh Muhammad Shairazi

Student Works (2020-2029)

Due to excellent mechanical and electrical properties, cross-linked polyethylene (XLPE) cables are commonly used in the power industry. However, cable joints are the weakest part of XLPE cables and are susceptible to insulation failures. Cable joint insulation breakup can cause large losses for power companies. It is therefore necessary to evaluate the consistency of the insulation for early detection of insulation failure. It is known that there is a link between the partial discharge (PD) and the quality of the insulation. PD analysis is an important tool for assessing the quality of insulation in cable joints. In this study, XLPE …

Classification Of Dividend News Based On The Movement Of The Share Market Prices Of Public Listed Companies In Bursa Malaysia, Vijaya Kumar Shubana

Student Works (2020-2029)

Stock market is naturally complex and plays a major role in towards the nation’s growth. However, the performance of a company in stock market varies due to many influences but not limited to economics, political and financial related news. This study attempts to classify the share market dividend news announcement in Bursa Malaysia based on the pattern of share market price. Samples including five hundred (500) observations of dividend news from forty-seven (47) listed companies in Bursa Malaysia during the period of 2000 to 2018 are used in this study. There are three (3) main objectives in this study which …

Content Based Image Retrieval (Cbir) For Brand Logos, Enjal Parajuli

Boise State University Theses and Dissertations

This thesis explores the problem of automatically detecting the presence of logos in general images. Brand logos carry the goodwill of a company and are considered to be of high value in the corporate world, and thus automatically determining whether or not a logo is present in an image can be of interest for companies that wish to protect their brand. The problem of automated logo detection is inherently complex, but is further complicated through intentional obfuscation of logo images, for example by color shifting or other slight image modifications that leave the logo intact and easily recognizable by a …

Obtaining Real-World Benchmark Programs From Open-Source Repositories Through Abstract-Semantics Preserving Transformations, Maria Anne Rachel Paquin

Boise State University Theses and Dissertations

Benchmark programs are an integral part of program analysis research. Researchers use benchmark programs to evaluate existing techniques and test the feasibility of new approaches. The larger and more realistic the set of benchmarks, the more confident a researcher can be about the correctness and reproducibility of their results. However, obtaining an adequate set of benchmark programs has been a long-standing challenge in the program analysis community.

In this thesis, we present the APT tool, a framework we designed and implemented to automate the generation of realistic benchmark programs suitable for program analysis evaluations. Our tool targets intra-procedural analyses that …