Digital Commons Network^™

Adaptive Learning Technique For Facial Recognition, Rachana Dineshkumar Bumb

Master's Theses

This research describes the adaptive learning technique for facial recognition. It is a common practice in convolutional neural network(CNN) based facial recognition to save its trained result on a large dataset and then load and apply it to ongoing facial recognition tasks. This generally used method lacks adaptation, and the ongoing evolution of new knowledge poses a key technical challenge. In this research, we propose a continued learning technique to incorporate new knowledge derived in each facial recognition process. A positive recognition with confidence score is assigned, and the image associated with this confidence is added to the image dataset …

Transfer Learning For Hyperspectral Images Utilizing Channel Selection Techniques And Ensemble Methods, Scott Daniel Vogel

Master's Theses

Hyperspectral images contain information from a wider range of the electromagnetic spectrum than natural images which gives them potential for better classification ability. However, hyperspectral datasets are typically small due to the expensive equipment needed to obtain the images, which can limit classification performance. One solution to this problem is transfer learning, in which a model trained on one dataset is reused for a separate dataset. Research has shown that transfer learning between hyperspectral datasets can give improved performance over models without transfer learning when training data are limited. Since extra hyperspectral data are not always available, the solution proposed …

Attentional Parsing Networks, Marcus Karr

Master's Theses

Convolutional neural networks (CNNs) have dominated the computer vision field since the early 2010s, when deep learning largely replaced previous approaches like hand-crafted feature engineering and hierarchical image parsing. Meanwhile transformer architectures have attained preeminence in natural language processing, and have even begun to supplant CNNs as the state of the art for some computer vision tasks.

This study proposes a novel transformer-based architecture, the attentional parsing network, that reconciles the deep learning and hierarchical image parsing approaches to computer vision. We recast unsupervised image representation as a sequence-to-sequence translation problem where image patches are mapped to successive layers …

Comparison Of Classification Algorithms And Undersampling Methods On Employee Churn Prediction: A Case Study Of A Tech Company, Heather Cooper

Master's Theses

Churn prediction is a common data mining problem that many companies face across industries. More commonly, customer churn has been studied extensively within the telecommunications industry where there is low customer retention due to high market competition. Similar to customer churn, employee churn is very costly to a company and by not deploying proper risk mitigation strategies, profits cannot be maximized, and valuable employees may leave the company. The cost to replace an employee is exponentially higher than finding a replacement, so it is in any company’s best interest to prioritize employee retention.

This research combines machine learning techniques with …

Combining Machine Learning And Empirical Engineering Methods Towards Improving Oil Production Forecasting, Andrew J. Allen

Master's Theses

Current methods of production forecasting such as decline curve analysis (DCA) or numerical simulation require years of historical production data, and their accuracy is limited by the choice of model parameters. Unconventional resources have proven challenging to apply traditional methods of production forecasting because they lack long production histories and have extremely variable model parameters. This research proposes a data-driven alternative to reservoir simulation and production forecasting techniques. We create a proxy-well model for predicting cumulative oil production by selecting statistically significant well completion parameters and reservoir information as independent predictor variables in regression-based models. Then, principal component analysis (PCA) …

Identification Of Users Via Ssh Timing Attack, Thomas J. Flucke

Master's Theses

Secure Shell, a tool to securely access and run programs on a remote machine, is an important tool for both system administrators and developers alike. The technology landscape is becoming increasingly distributed and reliant on tools such as Secure Shell to protect information as a user works on a system remotely. While Secure Shell accounts for the abuses the security of older tools such as telnet overlook, it still has fundamental vulnerabilities which leak information about both the user and their activities through timing attacks. The OpenSSH client, the implementation included in all Linux, Mac, and Windows computers, sends each …

A Code Reputation System Using Ai And Blockchain Technology, Jeremy Chau

Master's Theses

Open source development is a method of development in which source code is developed using the combined skills of the public. A few examples of this sort of development would be the Chromium and Linux kernel projects hosted on GitHub. Open source development offers a wide variety of benefits and disadvantages. A main concern is when many people blindly trust developers without second thought. There is a lack of a rating system that judges those who develop code through open source means. This can call into question the quality of the code being written by the individual as well as …

Web Conference Summarization Through A System Of Flags, Annirudh M. Ankola

Master's Theses

In today’s world, we are always trying to find new ways to advance. This era has given rise to a global, distributed workforce since technology has allowed people to access and communicate with individuals all over the world. With the rise of remote workers, the need for quality communication tools has risen significantly. These communication tools come in many forms, and web-conference apps are among the most prominent for the task. Developing a system to automatically summarize the web-conference will save companies time and money, leading to more efficient meetings. Current approaches to summarizing multi-speaker web-conferences tend to yield poor …

Optimizing Gene Expression Prediction And Omics Integration In Populations Of African Ancestry, Paul Chukwuebuka Okoro

Master's Theses

Popular transcriptome imputation methods such as PrediXcan and FUSIon use parametric linear assumptions, and thus are unable to flexibly model the complex genetic architecture of the transcriptome. Although non-linear modeling has been shown to improve imputation performance, replicability and potential cross-population differences have not been adequately studied. Therefore, to optimize imputation performance across global populations, we used the non-linear machine learning (ML) models random forest (RF), support vector regression (SVR), and K nearest neighbor (KNN) to build transcriptome imputation models, and evaluated their performance in comparison to elastic net (EN). We trained gene expression prediction models using genotype and blood …