Artificial Intelligence and Robotics Commons^™

Probing As A Technique To Understand Abstract Spaces, Ashlen A. Plasek

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

Machine learning models, while very powerful, have their operation obfuscated behind millions of parameters. This obfuscation can make deriving a human meaningful process from a machine learning model very difficult. However, while the intermediate states of a machine learning model are similarly obfuscated, using probing, we can start to explore looking at possible structure in those intermediate states. Large language models are a prime example of this obfuscation, and probing can begin to allow novel experimentation to be performed.

Machine Learning Data Feature Reduction And Model Optimization, Francisco P. Maturana, Phillip M. Lacasse

AFIT Patents

For machine learning data reduction and model optimization, a method randomly assigns each data feature of a training data set to a plurality of solution groups. Each solution group has no more than a solution group number k of data features and each data feature is assigned to a plurality of solution groups. The method identifies each solution group as a high-quality solution group or a low-quality solution group. The method further calculates data feature scores for each data feature comprising a high bin number and a low bin number. The method determines level data for each data feature from …

Towards An Experimental Bibliography Of Hemispheric Reconstruction Newspapers, Joshua Ortiz Baco, Benjamin Charles Germain Lee, Jim Casey, Sarah H. Salter

Criticism

Digital collections of newspapers have drawn broader attention to the fragmented and scattered print histories of minoritized communities. Attempts to survey these histories through bibliography, however, quickly meet with a fundamental problem: the practice of bibliographic description calls for creating a static record of social affiliations. Given the overwhelming scholarly consensus that categories such as race, ethnicity, and language are socially constructed, this article introduces an experimental bibliographic method for mapping the vast landscape of historical newspapers. This method extends the machine learning affordances of a recent project called Newspaper Navigator to enumerate the newspapers in Chronicling America according to …

Sarcasm Detection In English And Arabic Tweets Using Transformer Models, Rishik Lad

Computer Science Senior Theses

This thesis describes our approach toward the detection of sarcasm and its various types in English and Arabic Tweets through methods in deep learning. There are five problems we attempted: (1) detection of sarcasm in English Tweets, (2) detection of sarcasm in Arabic Tweets, (3) determining the type of sarcastic speech subcategory for English Tweets, (4) determining which of two semantically equivalent English Tweets is sarcastic, and (5) determining which of two semantically equivalent Arabic Tweets is sarcastic. All tasks were framed as classification problems, and our contributions are threefold: (a) we developed an English binary classifier system with RoBERTa, …

An Investigation Into Machine Learning Techniques For Designing Dynamic Difficulty Agents In Real-Time Games, Ryan Adare Dunagan

Electronic Theses and Dissertations

Video games are an incredibly popular pastime enjoyed by people of all ages world wide. Many different kinds of games exist, but most games feature some elements of the player overcoming some challenge, usually through gameplay. These challenges are insurmountable for some people and may turn them off to video games as a pastime. Games can be made more accessible to players of little skill and/or experience through the use of Dynamic Difficulty Adjustment (DDA) systems that adjust the difficulty of the game in response to the player’s performance. This research seeks to establish the effectiveness of machine learning techniques …

Artificial Intelligence Cad Tools In Trauma Imaging: A Scoping Review From The American Society Of Emergency Radiology (Aser) Ai/Ml Expert Panel, David Dreizin, Pedro V Staziaki, Garvit D Khatri, Nicholas M Beckmann, Zhaoyong Feng, Yuanyuan Liang, Zachary S Delproposto, Maximiliano Klug, J Stephen Spann, Nathan Sarkar, Yunting Fu

Faculty, Staff and Student Publications

BACKGROUND: AI/ML CAD tools can potentially improve outcomes in the high-stakes, high-volume model of trauma radiology. No prior scoping review has been undertaken to comprehensively assess tools in this subspecialty.

PURPOSE: To map the evolution and current state of trauma radiology CAD tools along key dimensions of technology readiness.

METHODS: Following a search of databases, abstract screening, and full-text document review, CAD tool maturity was charted using elements of data curation, performance validation, outcomes research, explainability, user acceptance, and funding patterns. Descriptive statistics were used to illustrate key trends.

RESULTS: A total of 4052 records were screened, and 233 full-text …

Automatic Scoring Of Speeded Interpersonal Assessment Center Exercises Via Machine Learning: Initial Psychometric Evidence And Practical Guidelines, Louis Hickman, Christoph N. Herde, Filip Lievens, Louis Tay

Research Collection Lee Kong Chian School Of Business

Assessment center (AC) exercises such as role-plays have established themselves as valuable approaches for obtaining insights into interpersonal behavior, but they are often considered the “Rolls Royce” of personnel assessment due to their high costs. The observation and rating process comprises a substantial part of these costs. In an exploratory case study, we capitalize on recent advances in natural language processing (NLP) by developing NLP-based machine learning (ML) models to investigate the possibility of automatically scoring AC exercises. First, we compared the convergent-related validity and contamination with word count of ML scores based on models that used different NLP methods …

Data-Optimized Spatial Field Predictions For Robotic Adaptive Sampling: A Gaussian Process Approach, Zachary Nathan

Computer Science Senior Theses

We introduce a framework that combines Gaussian Process models, robotic sensor measurements, and sampling data to predict spatial fields. In this context, a spatial field refers to the distribution of a variable throughout a specific area, such as temperature or pH variations over the surface of a lake. Whereas existing methods tend to analyze only the particular field(s) of interest, our approach optimizes predictions through the effective use of all available data. We validated our framework on several datasets, showing that errors can decline by up to two-thirds through the inclusion of additional colocated measurements. In support of adaptive sampling, …

Rapid Assessment Of Fish Freshness For Multiple Supply-Chain Nodes Using Multi-Mode Spectroscopy And Fusion-Based Artificial Intelligence, Hossein Kashani Zadeh, Mike Hardy, Mitchell Sueker, Yicong Li, Angelis Tzouchas, Nicholas Mackinnon, Gregory Bearman, Simon A Haughey, Alireza Akhbardeh, Insuck Baek, Chansong Hwang, Jianwei Qin, Amanda M Tabb, Rosalee S Hellberg, Shereen Ismail, Hassan Reza, Fartash Vasefi, Moon Kim, Kouhyar Tavakolian, Christopher T Elliott

Faculty, Staff and Student Publications

This study is directed towards developing a fast, non-destructive, and easy-to-use handheld multimode spectroscopic system for fish quality assessment. We apply data fusion of visible near infra-red (VIS-NIR) and short wave infra-red (SWIR) reflectance and fluorescence (FL) spectroscopy data features to classify fish from fresh to spoiled condition. Farmed Atlantic and wild coho and chinook salmon and sablefish fillets were measured. Three hundred measurement points on each of four fillets were taken every two days over 14 days for a total of 8400 measurements for each spectral mode. Multiple machine learning techniques including principal component analysis, self-organized maps, linear and …

Using Deep Neural Networks To Classify Astronomical Images, Andrew D. Macpherson

Honors Projects

As the quantity of astronomical data available continues to exceed the resources available for analysis, recent advances in artificial intelligence encourage the development of automated classification tools. This paper lays out a framework for constructing a deep neural network capable of classifying individual astronomical images by describing techniques to extract and label these objects from large images.

Automated Delineation Of Visual Area Boundaries And Eccentricities By A Cnn Using Functional, Anatomical, And Diffusion-Weighted Mri Data, Noah C. Benson, Bogeng Song, Toshikazu Miyata, Hiromasa Takemura, Jonathan Winawer

MODVIS Workshop

Delineating visual field maps and iso-eccentricities from fMRI data is an important but time-consuming task for many neuroimaging studies on the human visual cortex because the traditional methods of doing so using retinotopic mapping experiments require substantial expertise as well as scanner, computer, and human time. Automated methods based on gray-matter anatomy or a combination of anatomy and functional mapping can reduce these requirements but are less accurate than experts. Convolutional Neural Networks (CNNs) are powerful tools for automated medical image segmentation. We hypothesize that CNNs can define visual area boundaries with high accuracy. We trained U-Net CNNs with ResNet18 …

Ptmtorrent: A Dataset For Mining Open-Source Pre-Trained Model Packages, Wenxin Jiang, Nicholas Synovic, Purvish Jajal, Taylor R. Schorlemmer, Arav Tewari, Bhavesh Pareek, George K. Thiruvathukal, James C. Davis

Computer Science: Faculty Publications and Other Works

Due to the cost of developing and training deep learning models from scratch, machine learning engineers have begun to reuse pre-trained models (PTMs) and fine-tune them for downstream tasks. PTM registries known as “model hubs” support engineers in distributing and reusing deep learning models. PTM packages include pre-trained weights, documentation, model architectures, datasets, and metadata. Mining the information in PTM packages will enable the discovery of engineering phenomena and tools to support software engineers. However, accessing this information is difficult — there are many PTM registries, and both the registries and the individual packages may have rate limiting for accessing …

An Empirical Study Of Pre-Trained Model Reuse In The Hugging Face Deep Learning Model Registry, Wenxin Jiang, Nicholas Synovic, Matt Hyattt, Taylor R. Schorlemmer, Rohan Sethi, Yung-Hisang Lu, George K. Thiruvathukal, James C. Davis

Computer Science: Faculty Publications and Other Works

Deep Neural Networks (DNNs) are being adopted as components in software systems. Creating and specializing DNNs from scratch has grown increasingly difficult as state-of-the-art architectures grow more complex. Following the path of traditional software engineering, machine learning engineers have begun to reuse large-scale pre-trained models (PTMs) and fine-tune these models for downstream tasks. Prior works have studied reuse practices for traditional software packages to guide software engineers towards better package maintenance and dependency management. We lack a similar foundation of knowledge to guide behaviors in pre-trained model ecosystems.

In this work, we present the first empirical investigation of PTM reuse. …

Identifying Key Activity Indicators In Rats' Neuronal Data Using Lasso Regularized Logistic Regression, Avery Woods

Honors Theses

This thesis aims to identify timestamps of rats’ neuronal activity that best determine behavior using a machine learning model. Neuronal data is a complex and high-dimensional dataset, and identifying the most informative features is crucial for understanding the underlying neuronal processes. The Lasso regularization technique is employed to select the most relevant features of the data to the model’s prediction. The results of this study provide insights into the key activity indicators that are associated with specific behaviors or cognitive processes in rats, as well as the effect that stress can have on neuronal activity and behavior. Ultimately, it was …

U-No: U-Shaped Neural Operators, Md Ashiqur Rahman, Zachary E Ross, Kamyar Azizzadenesheli

Department of Computer Science Faculty Publications

Neural operators generalize classical neural networks to maps between infinite-dimensional spaces, e.g., function spaces. Prior works on neural operators proposed a series of novel methods to learn such maps and demonstrated unprecedented success in learning solution operators of partial differential equations. Due to their close proximity to fully connected architectures, these models mainly suffer from high memory usage and are generally limited to shallow deep learning models. In this paper, we propose U-shaped Neural Operator (U-NO), a U-shaped memory enhanced architecture that allows for deeper neural operators. U-NOs exploit the problem structures in function predictions and demonstrate fast training, data …

Tornado Outbreak False Alarm Probabilistic Forecasts With Machine Learning, Kirsten Reed Snodgrass

Theses and Dissertations

Tornadic outbreaks occur annually, causing fatalities and millions of dollars in damage. By improving forecasts, the public can be better equipped to act prior to an event. False alarms (FAs) can hinder the public’s ability (or willingness) to act. As such, a probabilistic FA forecasting scheme would be beneficial to improving public response to outbreaks.

Here, a machine learning approach is employed to predict FA likelihood from Storm Prediction Center (SPC) tornado outbreak forecasts. A database of hit and FA outbreak forecasts spanning 2010 – 2020 was developed using historical SPC convective outlooks and the SPC Storm Reports database. Weather …

Learning-Based Stock Trending Prediction By Incorporating Technical Indicators And Social Media Sentiment, Zhaoxia Wang, Zhenda Hu, Fang Li, Seng-Beng Ho, Erik Cambria

Research Collection School Of Computing and Information Systems

Stock trending prediction is a challenging task due to its dynamic and nonlinear characteristics. With the development of social platform and artificial intelligence (AI), incorporating timely news and social media information into stock trending models becomes possible. However, most of the existing works focus on classification or regression problems when predicting stock market trending without fully considering the effects of different influence factors in different phases. To address this gap, this research solves stock trending prediction problem utilizing both technical indicators and sentiments of the social media text as influence factors in different situations. A 3-phase hybrid model is proposed …

Information-Theoretic Model Diagnostics (Infomod), Armin Esmaeilzadeh

UNLV Theses, Dissertations, Professional Papers, and Capstones

Model validation is a critical step in the development, deployment, and governance of machine learning models. During the validation process, the predictive power of a model is measured on unseen datasets with a variety of metrics such as Accuracy and F1-Scores for classification tasks. Although the most used metrics are easy to implement and understand, they are aggregate measures over all the segments of heterogeneous datasets, and therefore, they do not identify the performance variation of a model among different data segments. The lack of insight into how the model performs over segments of unseen datasets has raised significant challenges …

Wearable Sensor Gait Analysis For Fall Detection Using Deep Learning Methods, Haben Girmay Yhdego

Electrical & Computer Engineering Theses & Dissertations

World Health Organization (WHO) data show that around 684,000 people die from falls yearly, making it the second-highest mortality rate after traffic accidents [1]. Early detection of falls, followed by pneumatic protection, is one of the most effective means of ensuring the safety of the elderly. In light of the recent widespread adoption of wearable sensors, it has become increasingly critical that fall detection models are developed that can effectively process large and sequential sensor signal data. Several researchers have recently developed fall detection algorithms based on wearable sensor data. However, real-time fall detection remains challenging because of the wide …

Lidar Buoy Detection For Autonomous Marine Vessel Using Pointnet Classification, Christopher Adolphi, Dorothy Dorie Parry, Yaohang Li, Masha Sosonkina, Ahmet Saglam, Yiannis E. Papelis

Modeling, Simulation and Visualization Student Capstone Conference

Maritime autonomy, specifically the use of autonomous and semi-autonomous maritime vessels, is a key enabling technology supporting a set of diverse and critical research areas, including coastal and environmental resilience, assessment of waterway health, ecosystem/asset monitoring and maritime port security. Critical to the safe, efficient and reliable operation of an autonomous maritime vessel is its ability to perceive on-the-fly the external environment through onboard sensors. In this paper, buoy detection for LiDAR images is explored by using several tools and techniques: machine learning methods, Unity Game Engine (herein referred to as Unity) simulation, and traditional image processing. The Unity Game …

On The Accelerated Noise-Tolerant Power Method, Zhiqiang Xu

Machine Learning Faculty Publications

We revisit the acceleration of the noise-tolerant power method for which, despite previous studies, the results remain unsatisfactory as they are either wrong or suboptimal, also lacking generality. In this work, we present a simple yet general and optimal analysis via noise-corrupted Chebyshev polynomials, which allows a larger iteration rank p than the target rank k, requires less noise conditions in a new form, and achieves the optimal iteration complexity (Equation presented) for some q satisfying k ≤ q ≤ p in a certain regime of the momentum parameter. Interestingly, it shows dynamic dependence of the noise tolerance on the …

Socially Aware Natural Language Processing With Commonsense Reasoning And Fairness In Intelligent Systems, Sirwe Saeedi

Dissertations

Although Artificial Intelligence (AI) promises to deliver ever more user-friendly consumer applications, recent mishaps involving fake information and biased treatment serve as vivid reminders of the pitfalls of AI. AI can harbor latent biases and flaws that can cause harm in diverse and unexpected ways. It is crucial to understand the reasons for, mechanisms behind, and circumstances under which AI can fail. For instance, a lack of commonsense reasoning can lead to biased or unfair decisions made by Machine Learning (ML) systems. For example, if an ML system is trained on data that is biased or unrepresentative of the real …

Applications Of Generative Adversarial Networks In Single Image Datasets, Dylan E. Cramer

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

One of the main difficulties faced in most generative machine learning models is how much data is required to train it, especially when collecting a large dataset is not feasible. Recently there have been breakthroughs in tackling this issue in SinGAN, with its researchers being able to train a Generative Adversarial Network (GAN) on just a single image with a model that can perform many novel tasks, such as image harmonization. ConSinGAN is a model that builds upon this work by concurrently training several stages in a sequential multi-stage manner while retaining the ability to perform those novel tasks.

Design, Determination, And Evaluation Of Gender-Based Bias Mitigation Techniques For Music Recommender Systems, Sunny Shrestha

Electronic Theses and Dissertations

The majority of smartphone users engage with a recommender system on a daily basis. Many rely on these recommendations to make their next purchase, download the next game, listen to the new music or find the next healthcare provider. Although there are plenty of evidence backed research that demonstrates presence of gender bias in Machine Learning (ML) models like recommender systems, the issue is viewed as a frivolous cause that doesn’t merit much action. However, gender bias poses to effect more than half of the population as by default ML systems are designed to cater to a cisgender man. This …

Solving Fjssp With A Genetic Algorithm, Michael John Srouji

Computer Science and Software Engineering

The Flexible Job Shop Scheduling Problem is an NP-Hard combinatorial problem. This paper aims to find a solution to this problem using genetic algorithms, and discuss the effectiveness of this. Initially, I did exploratory work on whether neural networks would be effective or not, and found a lot of trade offs between using neural networks and chromosome sequencing. In the end, I decided to use chromosome sequencing over neural networks, due to the scope of my problem being on a small scale rather than on a large scale.

Therefore, the genetic algorithm was implemented using chromosome sequencing. My chromosomes were …

The Use Of Artificial Intelligence To Detect Students Sentiments And Emotions In Gross Anatomy Reflections, Krzysztof J. Rechowicz, Carrie A. Elzie

VMASC Publications

Students' reflective writings in gross anatomy provide a rich source of complex emotions experienced by learners. However, qualitative approaches to evaluating student writings are resource heavy and timely. To overcome this, natural language processing, a nascent field of artificial intelligence that uses computational techniques for the analysis and synthesis of text, was used to compare health professional students' reflections on the importance of various regions of the body to their own lives and those of the anatomical donor dissected. A total of 1365 anonymous writings (677 about a donor, 688 about self) were collected from 132 students. Binary and trinary …

Machine Learning Methods For Computational Phenotyping Using Patient Healthcare Data With Noisy Labels, Praveen Kumar

Computer Science ETDs

Positive and Unlabeled (PU) learning problems abound in many real-world applications. In healthcare informatics, diagnosed patients are considered labeled positive for a specific disease, but being undiagnosed does not mean they can be labeled negative. PU learning can improve classification performance, and estimate the positive fraction, α, among unlabeled samples. However, algorithms based on the Selected Completely At Random (SCAR) assumption are inadequate when the SCAR assumption fails (e.g., severe cases overrepresented), and when class imbalance is substantial. This dissertation presents and evaluates new algorithms to overcome these limitations. The proposed methods outperform the state-of-art for α-estimation, enhance classification performance, …

Emotion Classification Of Indonesian Tweets Using Bidirectional Lstm, Aaron K. Glenn, Phillip M. Lacasse, Bruce A. Cox

Faculty Publications

Emotion classification can be a powerful tool to derive narratives from social media data. Traditional machine learning models that perform emotion classification on Indonesian Twitter data exist but rely on closed-source features. Recurrent neural networks can meet or exceed the performance of state-of-the-art traditional machine learning techniques using exclusively open-source data and models. Specifically, these results show that recurrent neural network variants can produce more than an 8% gain in accuracy in comparison with logistic regression and SVM techniques and a 15% gain over random forest when using FastText embeddings. This research found a statistical significance in the performance of …

Predicting Suicidal And Self-Injurious Events In A Correctional Setting Using Ai Algorithms On Unstructured Medical Notes And Structured Data, Hongxia Lu, Alex Barrett, Albert Pierce, Jianwei Zheng, Yun Wang, Chun Chiang, Cyril Rakovski

Mathematics, Physics, and Computer Science Faculty Articles and Research

Suicidal and self-injurious incidents in correctional settings deplete the institutional and healthcare resources, create disorder and stress for staff and other inmates. Traditional statistical analyses provide some guidance, but they can only be applied to structured data that are often difficult to collect and their recommendations are often expensive to act upon. This study aims to extract information from medical and mental health progress notes using AI algorithms to make actionable predictions of suicidal and self-injurious events to improve the efficiency of triage for health care services and prevent suicidal and injurious events from happening at California's Orange County Jails. …

A Machine Learning Approach To Deepfake Detection, Delaney Conrad

All Undergraduate Theses and Capstone Projects

The ability to manipulate videos has been around for decades but a process that once would take time, money, and professionals, can now be created by anyone due to the rapid advancement of deepfake technology. Deepfakes use deep learning artificial intelligence to make fake digital content, typically in the form of swapping a person’s face in a video or image. This technology could easily threaten and manipulate individuals, corporations, and political organizations, so it is essential to find methods for detecting deepfakes. As the technology for creating deepfakes continues to improve, these manipulated videos are becoming increasingly undetectable. It is …