Computer Sciences Commons^™

Fridge Tracker And Recipe Provider : Fridgechamp, Matt Dudek

Williams Honors College, Honors Research Projects

FridgeChamp is a website to allow people to track their fridge/pantry contents while providing them recipes they can make with said ingredients. Currently there are few ingredient trackers and recipe matchers that exist as websites, and of those many lack simplistic recipes that a home chef would use. In addition to lacking some recipes, many tracker/recipe apps do not have a function to remove from your stock what a recipe requires, making you tediously update the stock every time you cook/use something.

Unsupervised-Based Distributed Machine Learning For Efficient Data Clustering And Prediction, Vishnu Vardhan Baligodugula

Browse all Theses and Dissertations

Machine learning techniques utilize training data samples to help understand, predict, classify, and make valuable decisions for different applications such as medicine, email filtering, speech recognition, agriculture, and computer vision, where it is challenging or unfeasible to produce traditional algorithms to accomplish the needed tasks. Unsupervised ML-based approaches have emerged for building groups of data samples known as data clusters for driving necessary decisions about these data samples and helping solve challenges in critical applications. Data clustering is used in multiple fields, including health, finance, social networks, education, and science. Sequential processing of clustering algorithms, like the K-Means, Minibatch K-Means, …

Anomaly Detection In Multi-Seasonal Time Series Data, Ashton Taylor Williams

Browse all Theses and Dissertations

Most of today’s time series data contain anomalies and multiple seasonalities, and accurate anomaly detection in these data is critical to almost any type of business. However, most mainstream forecasting models used for anomaly detection can only incorporate one or no seasonal component into their forecasts and cannot capture every known seasonal pattern in time series data. In this thesis, we propose a new multi-seasonal forecasting model for anomaly detection in time series data that extends the popular Seasonal Autoregressive Integrated Moving Average (SARIMA) model. Our model, named multi-SARIMA, utilizes a time series dataset’s multiple pre-determined seasonal trends to increase …

Path-Safe: Enabling Dynamic Mandatory Access Controls Using Security Tokens, James P. Maclennan

Browse all Theses and Dissertations

Deploying Mandatory Access Controls (MAC) is a popular way to provide host protection against malware. Unfortunately, current implementations lack the flexibility to adapt to emergent malware threats and are known for being difficult to configure. A core tenet of MAC security systems is that the policies they are deployed with are immutable from the host while they are active. This work looks at deploying a MAC system that leverages using encrypted security tokens to allow for redeploying policy configurations in real-time without the need to stop a running process. This is instrumental in developing an adaptive framework for security systems …

Data-Driven Strategies For Disease Management In Patients Admitted For Heart Failure, Ankita Agarwal

Browse all Theses and Dissertations

Heart failure is a syndrome which effects a patient’s quality of life adversely. It can be caused by different underlying conditions or abnormalities and involves both cardiovascular and non-cardiovascular comorbidities. Heart failure cannot be cured but a patient’s quality of life can be improved by effective treatment through medicines and surgery, and lifestyle management. As effective treatment of heart failure incurs cost for the patients and resource allocation for the hospitals, predicting length of stay of these patients during each hospitalization becomes important. Heart failure can be classified into two types: left sided heart failure and right sided heart failure. …

Understanding And Enhancing The Efficiency And Efficacy Of Machine Learning-Assisted Software Vulnerability Detection, Daniel J. Grahn

Browse all Theses and Dissertations

As our world has become dependent upon software for nearly every aspect of modern society, software security has followed as an essential feature. The first line of defense against vulnerabilities is secure coding. While today’s programmers are carefully taught secure coding best practices, they can make mistakes or intentionally introduce vulnerable code. The traditional backstop to human errors and insider threats is the adoption of automated security analysis tools. These analysis tools have limitations. Static analysis suffers from high false positive rates that may cause annoyance and complacency among developers. Dynamic analysis can be difficult to set up and very …

"You Shouldn't Need To Share Your Data": Perceived Privacy Risks And Mitigation Strategies Among Privacy-Conscious Smart Home Power Users, Anna Lenhart, Sunyup Park, Michael Zimmer, Jessica Vitak

Computer Science Faculty Research and Publications

Fueled by Internet-of-Things technologies and spanning a wide range of sensors, speakers, and cameras, smart homes promise to make our lives easier and automate routine tasks. From speakers to security cameras, smart home devices (SHDs) answer our questions, monitor our home environment, and conserve energy. They also collect significant data, ranging from on/off commands to audio and video data, and they do this in some of our most private spaces. In this paper, we explore the privacy risks associated with SHDs by focusing on privacy-conscious smart home power users--those who spend significant time and money to research, install, and integrate …

Power, Stress, And Uncertainty: Experiences With And Attitudes Toward Workplace Surveillance During A Pandemic, Jessica Vitak, Michael Zimmer

Computer Science Faculty Research and Publications

There is a rich literature on technology’s role in facilitating employee monitoring in the workplace. The COVID-19 pandemic created many challenges for employers, and many companies turned to new forms of monitoring to ensure remote workers remained productive; however, these technologies raise important privacy concerns as the boundaries between work and home are further blurred. In this paper, we present findings from a study of 645 US workers who spent at least part of 2020 working remotely due to the pandemic. We explore how their work experiences (job satisfaction, stress, and security) changed between January and November 2020, as well …

Invasive Buckthorn Mapping: A Uav-Based Approach Utilizing Machine Learning, Gis, And Remote Sensing Techniques In The Upper Peninsula Of Michigan, Vikranth Madeppa

Dissertations, Master's Theses and Master's Reports

An Invasive species is a species that is alien or non-native to the ecosystem which causes harm to economic, environmental, or human health (E.O. 13112 of Feb 3, 1999). Invasive species have posed a serious threat to ecosystems across the globe. These invasive species have impacts on the biodiversity and productivity of invaded forests. Remotely sensed data is a valuable resource for understanding and addressing issues related to invasive species. This study presents a novel approach for mapping the distribution of two invasive plant species, Common and Glossy Buckthorn, using unmanned aerial vehicles (UAVs), machine learning algorithms, geographic information systems …

Exploring High Performance And Energy Efficient Graph Processing On Gpu, Robert P. Watling

Dissertations, Master's Theses and Master's Reports

Parallel graph processing is central to analytical computer science applications, and GPUs have proven to be an ideal platform for parallel graph processing. Existing GPU graph processing frameworks present performance improvements but often neglect two issues: the unpredictability of a given input graph and the energy consumption of the graph processing. Our prototype software, EEGraph (Energy Efficiency of Graph processing), is a flexible system consisting of several graph processing algorithms with configurable parameters for vertex update synchronization, vertex activation, and memory management along with a lightweight software-based GPU energy measurement scheme. We observe relationships between different configurations of our software, …

Exploring Different Mediums For Teaching Programming And Cybersecurity In Primary And Secondary Schools, Andrew R. Youngstrom

Dissertations, Master's Theses and Master's Reports

Cybersecurity and programming are becoming more and more prominent in today’s world. It is beneficial to begin teaching these topics to students at a younger age. Additionally, we see students in primary and secondary schools struggling to maintain focus in class as attention spans shrink. This paper looks at different drone models to see if any of them could be sufficient solutions to be implemented into primary and secondary schools to teach cybersecurity and programming topics to students. Besides teaching capabilities, drones must also be affordable for institutions and simple enough to construct, configure, and operate so that a teacher …

Prediction Of Sumoylation Sites In Proteins From Language Model Representations, Evgenii Sidorov

Dissertations, Master's Theses and Master's Reports

Sumoylation is an essential post-translational modification intimately involved in a diverse range of eukaryotic cellular mechanisms and plays a significant role in DNA repair. Some researchers hypothesize that a high level of SUMOylation events in cancer cells improves cells' chances for survival under stress conditions by regulating tumor-related proteins.

This study belongs to a booming field of harnessing computational power to the domain of life. Prediction of protein structure, its molecular function, and the design of new drugs are just a few examples of the applications within this exciting area of research. By leveraging computational power, researchers can analyze vast …

Knowledge Discovery On The Integrative Analysis Of Electrical And Mechanical Dyssynchrony To Improve Cardiac Resynchronization Therapy, Zhuo He

Dissertations, Master's Theses and Master's Reports

Cardiac resynchronization therapy (CRT) is a standard method of treating heart failure by coordinating the function of the left and right ventricles. However, up to 40% of CRT recipients do not experience clinical symptoms or cardiac function improvements. The main reasons for CRT non-response include: (1) suboptimal patient selection based on electrical dyssynchrony measured by electrocardiogram (ECG) in current guidelines; (2) mechanical dyssynchrony has been shown to be effective but has not been fully explored; and (3) inappropriate placement of the CRT left ventricular (LV) lead in a significant number of patients.

In terms of mechanical dyssynchrony, we utilize an …

Explicit Rule Learning: A Cognitive Tutorial Method To Train Users Of Artificial Intelligence/Machine Learning Systems, Anne Linja

Dissertations, Master's Theses and Master's Reports

Today’s intelligent software systems, such as Artificial Intelligence/Machine Learning systems, are sophisticated, complicated, sometimes complex systems. In order to effectively interact with these systems, novice users need to have a certain level of understanding. An awareness of a system’s underlying principles, rationale, logic, and goals can enhance the synergistic human-machine interaction. It also benefits the user to know when they can trust the systems’ output, and to discern boundary conditions that might change the output. The purpose of this research is to empirically test the viability of a Cognitive Tutorial approach, called Explicit Rule Learning. Several approaches have been used …

Design And Implementation Of A Graphql Mesh Gateway: Federating Api Endpoints Based On A Defined Data Model, Marcus D. Scese

Dissertations, Master's Theses and Master's Reports

This paper introduces the GraphQL Mesh federated API (Application Programming Interface) gateway project, a comprehensive initiative implemented using GraphQL Mesh to solve data related issues within the USW-DSS (Undersea Warfare - Decision Support System). The project contributes to the evolving discourse on the pivotal role of Data Fabrics and Data Meshes in dismantling the barriers imposed by digital data silos. The project is a collaboration between researchers at Michigan Technological University, and engineers at ARiA (Applied Research in Acoustics LLC). The aim of the project is to resolve difficulties in understanding a large collection of API endpoints. By navigating the …

The Impact Of Pre-Experiment Walking On Distance Perception In Vr, Soheil Sepahyar

Dissertations, Master's Theses and Master's Reports

While individuals can accurately estimate distances in the real world, this ability is often diminished in virtual reality (VR) simulations, hampering performance across training, entertainment, prototyping, and education domains. To assess distance judgments, the direct blind walking method—having participants walk blindfolded to targets—is frequently used. Typically, direct blind walking measurements are performed after an initial practice phase, where people become comfortable with walking while blindfolded. Surprisingly, little research has explored how such pre-experiment walking impacts subsequent VR distance judgments. Our initial investigation revealed increased pre-experiment blind walking reduced distance underestimations, underscoring the importance of detailing these preparatory procedures in research—details …

An Ambiguous Technique For Nonvisual Text Entry, Dylan C. Gaines

Dissertations, Master's Theses and Master's Reports

Text entry is a common daily task for many people, but it can be a challenge for people with visual impairments when using virtual touchscreen keyboards that lack physical key boundaries. In this thesis, we investigate using a small number of gestures to select from groups of characters to remove most or all dependence on touch locations. We leverage a predictive language model to select the most likely characters from the selected groups once a user completes each word.

Using a preliminary interface with six groups of characters based on a Qwerty keyboard, we find that users are able to …

Novel Bayesian Neural Networks And Uncertainty Quantification Of Computational Mechanics Models, Ponkrshnan Thiagarajan

Dissertations, Master's Theses and Master's Reports

Computational and data-driven models suffer from a wide range of uncertainties that impact the reliability of such models. Given the exponential proliferation of machine learning models in real-world systems, establishing a degree of confidence in their predictions becomes paramount. Reliability in predictions takes on utmost significance in domains such as autonomous driving, medical image analysis, etc., where human lives are involved, and inaccuracies in predictions could lead to disastrous outcomes. For these reasons, comprehending and quantifying uncertainties in computational and data-driven models is of utmost importance. A number of techniques have been developed to quantify uncertainties in machine learning models. …

Deep Learning For Medical Image Segmentation Using Prior Knowledge And Topology, Chen Zhao

Dissertations, Master's Theses and Master's Reports

Image segmentation refers to the division of a digital image into distinct segments or groups of pixels/voxels. However, most of the existing deep learning approaches lack the utilization of prior knowledge, such as shape information, which could improve segmentation accuracy. In addition, conventional image segmentation frequently falls short in preserving intricate spatial details, motivating the innovation of strategies for multi-scaled feature integration. Furthermore, traditional image segmentation methods primarily concentrate on pixel-level or region-level analysis. However, given the inherent morphological similarities among various image objects, the significance of topology information surpasses that of pixel-level data in the realm of medical image …

Image Captioning Using Reinforcement Learning, Venkat Teja Golamaru

Master's Projects

Image captioning is a crucial technology with numerous applications, including enhancing accessibility for the visually impaired, developing automated image indexing and retrieval systems, and enriching social media experiences. However, accurately describing the content of an image in natural language remains a challenge, particularly in low-resource settings where data and computational power are limited. The most advanced image captioning architectures currently use encoder-decoder structures that incorporate a sequential recurrent prediction model. This study adopts a typical Convolutional Neural Network (CNN) encoder Recurrent Neural Network (RNN) decoder structure for image captioning, but it has framed the problem as a sequential decision-making task. …

Gender Classification Via Human Joints Using Convolutional Neural Network, Cheng-En Sung

Master's Projects

With the growing demand for gender-related data on diverse applications, including security systems for ascertaining an individual’s identity for border crossing, as well as marketing purposes of digging the potential customer and tailoring special discounts for them, gender classification has become an essential task within the field of computer vision and deep learning. There has been extensive research conducted on classifying human gender using facial expression, exterior appearance (e.g., hair, clothes), or gait movement. However, within the scope of our research, none have specifically focused gender classification on two-dimensional body joints. Knowing this, we believe that a new prediction pipeline …

Job Tailored Resume Content Generation, Sumedh Kale

Master's Projects

Generally candidates apply to multiple jobs with a single resume and do not tend to customize their resume to match the job description. This hampers their chances of getting a resume shortlisted for the job. The project aims to help such candidates build job tailored resumes that help them create a customized and targeted resume for a specific job or industry. The tool specifically targets candidates’ employment history, for resume content generation. We then use natural language processing

(NLP) techniques to extract and organize this data into a structured format for the dataset. We experiment with multiple variations of the …

Spartanscript: New Language Design For Smart Contracts, Ajinkya Lakade

Master's Projects

Smart contracts have become a crucial element for developing decentralized applications on blockchain, resulting in numerous innovative projects on blockchain networks. Ethereum has played a significant role in this space by providing a high-performance Ethereum virtual machine, enabling the creation of several high- level programming languages that can run on the Ethereum blockchain. Despite its usefulness, the Ethereum Virtual Machine has been prone to security vulnerabilities that can result in developers succumbing to common pitfalls which are otherwise safeguarded by modern virtual machines used in programming languages. The project aims to introduce a new interpreted scripting programming language that closely …

Codeval, Aditi Agrawal

Master's Projects

Grading coding assignments call for a lot of work. There are numerous aspects of the code that need to be checked, such as compilation errors, runtime errors, the number of test cases passed or failed, and plagiarism. Automated grading tools for programming assignments can be used to help instructors and graders in evaluating the programming assignments quickly and easily. Creating the assignment on Canvas is again a time taking process and can be automated. We developed CodEval, which instantly grades the student assignment submitted on Canvas and provides feedback to the students. It also uploads, creates, and edits assignments, thereby …

Multi-Label Text Classification With Transfer Learning, Likhitha Yelamanchili

Master's Projects

Multi-label text categorization is a crucial task in Natural Language Processing, where each text instance can be simultaneously assigned to numerous labels. This project's goal is to assess how well several deep learning models perform on a real-world dataset for multi-label text classification. We employed data augmentation techniques like Synonym Substitution and Random Word Substitution to address the problem of data imbalance. We conducted experiments on a toxic comment classification dataset to evaluate the effectiveness of several deep learning models including Bi-LSTM, GRU, and Bi-GRU, as well as fine- tuned pre-trained BERT models. Many metrics, including log loss, recall@k, and …

Resource Coordination Learning For End-To-End Network Slicing Under Limited State Visibility, Xiang Liu

Master's Projects

This paper discusses a resource coordination problem under limited state visibility to realize end-to-end network slices that are hosted by multiple network domains. We formulate this resource coordination problem as a special type of the multi- armed bandit (MAB) problem called the combinatorial multi-armed bandit (CMAB) problem. Based on this formulation, we convert the problem to a regret minimization problem with a linear objective function and solve it by adapting the Learning with Linear Rewards (LLR) algorithm. In this paper, we present a new hybrid approach that incorporates state reports, which include partial resource information in each domain, into the …

Container Caching Optimization Based On Explainable Deep Reinforcement Learning, Divyashree Jayaram

Master's Projects

Serverless edge computing environments use lightweight containers to run IoT services on a need basis i.e only when a service is requested. These containers experience a cold start up latency when starting up. One probable solution to reduce the startup delay is container caching on the edge nodes. Edge nodes are nodes that are closer in proximity to the IoT devices. Efficient container caching strategies are required since the resource availability on these edge devices is limited. Because of this constraint on resources, the container caching strategies should also take proper resource utilization into account. This project tries to further …

Relationalnet Using Graph Neural Networks For Social Recommendations, Dharahas Tallapally

Master's Projects

Traditional recommender systems create models that can predict user interests based on the user-item relationships. However, these systems often have limited performance due to sparse user behavior data. To address this challenge, researchers are now exploring models for social recommendation that can account for both user- user and user-item relationships based on social networks, and user past behavior, respectively. These models aim to understand each user’s behavior by considering their trusted neighbors and their influence on each other. Specifically, the potential embedding of each user is influenced by their trusted neighbors, who are, in turn, influenced by their own trusted …

Image Classification Using Ensemble Modeling And Deep Learning, Kaneesha Gandhi

Master's Projects

With the advances in technology, image classification has become one of the core areas of interest for researchers in the field of computer vision. We, humans, experience great levels of visuals in our day-to-day lives. The human eye is a powerful tool that not only lets us capture images around us but also aids in remembering, distinguishing, and interpreting these visuals. Comprehending the images that the user perceives is an important application in the fields of artificial intelligence, smart security systems, and areas of virtual reality. Recent advances in machine learning and neural networks have led to more precise and …

Base Station Load Prediction In 5g-V2x Handover, Madhujita Ranjit Ambaskar

Master's Projects

5G V2X networks transmit large amounts of data with low latency, allowing for real-time communication between vehicles and other infrastructure. In 5G V2X networks, handover is a process that allows a connected vehicle to transfer its con- nection from one base station to another as it moves through the network coverage area. Handover is critical to maintaining the quality of service (QoS) and ensuring uninterrupted communication. The base station load is a critical factor in ensuring reliable and efficient 5G V2X connectivity. Prediction of traffic load on base stations ensure resource optimization and smooth connectivity during handovers. This research predicts …