Artificial Intelligence and Robotics Commons^™

Source Code Comment Classification Artificial Intelligence, Cole Sutyak

Williams Honors College, Honors Research Projects

Source code comment classification is an important problem for future machine learning solutions. In particular, supervised machine learning solutions that have largely subjective data labels but are difficult to obtain the labels for. Machine learning problems are problems largely because of a lack of data. In machine learning solutions, it is better to have a large amount of mediocre data than it is to have a small amount of good data. While the mediocre data might not produce the best accuracy, it produces the best results because there is much more to learn from the problem.

In this project, data …

Learning From Multi-Class Imbalanced Big Data With Apache Spark, William C. Sleeman Iv

Theses and Dissertations

With data becoming a new form of currency, its analysis has become a top priority in both academia and industry, furthering advancements in high-performance computing and machine learning. However, these large, real-world datasets come with additional complications such as noise and class overlap. Problems are magnified when with multi-class data is presented, especially since many of the popular algorithms were originally designed for binary data. Another challenge arises when the number of examples are not evenly distributed across all classes in a dataset. This often causes classifiers to favor the majority class over the minority classes, leading to undesirable results …

Detecting Surface Interactions Via A Wearable Microphone To Improve Augmented Reality Text Entry, R. Habibi

Dissertations, Master's Theses and Master's Reports

This thesis investigates whether we can detect and distinguish between surface interaction events such as tapping or swiping using a wearable mic from a surface. Also, what are the advantages of new text entry methods such as tapping with two fingers simultaneously to enter capital letters and punctuation? For this purpose, we conducted a remote study to collect audio and video of three different ways people might interact with a surface. We also built a CNN classifier to detect taps. Our results show that we can detect and distinguish between surface interaction events such as tap or swipe via a …

Weakly Supervised Learning For Multi-Image Synthesis, Muhammad Usman Rafique

Theses and Dissertations--Electrical and Computer Engineering

Machine learning-based approaches have been achieving state-of-the-art results on many computer vision tasks. While deep learning and convolutional networks have been incredibly popular, these approaches come at the expense of huge amounts of labeled data required for training. Manually annotating large amounts of data, often millions of images in a single dataset, is costly and time consuming. To deal with the problem of data annotation, the research community has been exploring approaches that require less amount of labelled data.

The central problem that we consider in this research is image synthesis without any manual labeling. Image synthesis is a classic …

Scaling Up Exact Neural Network Compression By Relu Stability, Thiago Serra, Xin Yu, Abhinav Kumar, Srikumar Ramalingam

Faculty Conference Papers and Presentations

We can compress a rectifier network while exactly preserving its underlying functionality with respect to a given input domain if some of its neurons are stable. However, current approaches to determine the stability of neurons with Rectified Linear Unit (ReLU) activations require solving or finding a good approximation to multiple discrete optimization problems. In this work, we introduce an algorithm based on solving a single optimization problem to identify all stable neurons. Our approach is on median 183 times faster than the state-of-art method on CIFAR-10, which allows us to explore exact compression on deeper (5 x 100) and wider …

The Enlightening Role Of Explainable Artificial Intelligence In Chronic Wound Classification, Salih Sarp, Murat Kuzlu, Emmanuel Wilson, Umit Cali, Ozgur Guler

Engineering Technology Faculty Publications

Artificial Intelligence (AI) has been among the most emerging research and industrial application fields, especially in the healthcare domain, but operated as a black-box model with a limited understanding of its inner working over the past decades. AI algorithms are, in large part, built on weights calculated as a result of large matrix multiplications. It is typically hard to interpret and debug the computationally intensive processes. Explainable Artificial Intelligence (XAI) aims to solve black-box and hard-to-debug approaches through the use of various techniques and tools. In this study, XAI techniques are applied to chronic wound classification. The proposed model classifies …

Food/Non-Food Classification Of Real-Life Egocentric Images In Low- And Middle-Income Countries Based On Image Tagging Features, Guangzong Chen, Wenyan Jia, Yifan Zhao, Zhi-Hong Mao, Benny Lo, Alex K Anderson, Gary Frost, Modou L Jobarteh, Megan A Mccrory, Edward Sazonov, Matilda Steiner-Asiedu, Richard S Ansong, Thomas Baranowski, Lora Burke, Mingui Sun

Children’s Nutrition Research Center Staff Publications

Malnutrition, including both undernutrition and obesity, is a significant problem in low- and middle-income countries (LMICs). In order to study malnutrition and develop effective intervention strategies, it is crucial to evaluate nutritional status in LMICs at the individual, household, and community levels. In a multinational research project supported by the Bill & Melinda Gates Foundation, we have been using a wearable technology to conduct objective dietary assessment in sub-Saharan Africa. Our assessment includes multiple diet-related activities in urban and rural families, including food sources (e.g., shopping, harvesting, and gathering), preservation/storage, preparation, cooking, and consumption (e.g., portion size and nutrition analysis). …

Maidrl: Semi-Centralized Multi-Agent Reinforcement Learning Using Agent Influence, Anthony Lee Harris

Graduate Theses/Dissertations

In recent years, reinforcement learning algorithms, a subset of machine learning that focuses on solving problems through trial-and-error learning, have been used in the field of multi-agent systems to help the agents with interactions and cooperation on a variety of tasks. Given the enormous success of reinforcement learning in single-agent systems like Chess, Shogi, and Go, it is natural for the next step to be the expansion into multi-agent systems. However, controlling multiple agents simultaneously is extremely challenging, as the complexity increases tremendously with the number of agents in the system. Existing approaches in this regard use a wide range …

How Much Can Potential Jurors Tell Us About Liability For Medical Artificial Intelligence?, W. Nicholson Price Ii, Sara Gerke, I. Glenn Cohen

Articles

Artificial intelligence (AI) is rapidly entering medical practice, whether for risk prediction, diagnosis, or treatment recommendation. But a persistent question keeps arising: What happens when things go wrong? When patients are injured, and AI was involved, who will be liable and how? Liability is likely to influence the behavior of physicians who decide whether to follow AI advice, hospitals that implement AI tools for physician use, and developers who create those tools in the first place. If physicians are shielded from liability (typically medical malpractice liability) when they use AI tools, even if patient injury results, they are more likely …

Statistical And Machine Learning Approaches To Depressive Disorders Among Adults In The United States: From Factor Discovery To Prediction Evaluation, Minhwa Lee

Senior Independent Study Theses

According to the National Institutes of Mental Health (NIMH), depressive disorders (or major depression) are considered one of the most common and serious health risks in the United States. Our study focuses on extracting non-medical factors of depressive disorders diagnosis, such as overall health states, health risk behaviors, demography, and healthcare access, using the Behavioral Risk Factor Surveillance System (BRFSS) data set collected by the Centers for Disease Control and Prevention (CDC) in 2018.

We set the two objectives of our study about depressive disorders diagnosis in the United States as follows. First, we aim to utilize machine learning algorithms …

A Methodology For Detecting Credit Card Fraud, Kayode Ayorinde

All Graduate Theses, Dissertations, and Other Capstone Projects

Fraud detection has appertained to many industries such as banking, retails, financial services, healthcare, etc. As we know, fraud detection is a set of campaigns undertaken to avert the acquisition of illegal means to obtain money or property under false pretense. With an unlimited and growing number of ways fraudsters commit fraud crimes, detecting online fraud was so tricky to achieve. This research work aims to examine feasible ways to identify credit card fraudulent activities that negatively impact financial institutes. In the United States, an average of U.S consumers lost a median of $429 from credit card fraud in 2017, …

A Tool For Segmentation Of Secondary Structures In 3d Cryo-Em Density Map Components Using Deep Convolutional Neural Networks, Yongcheng Mu, Salim Sazzed, Maytha Alshammari, Jiangwen Sun, Jing He

Computer Science Faculty Publications

Although cryo-electron microscopy (cryo-EM) has been successfully used to derive atomic structures for many proteins, it is still challenging to derive atomic structures when the resolution of cryo-EM density maps is in the medium resolution range, such as 5–10 Å. Detection of protein secondary structures, such as helices and β-sheets, from cryo-EM density maps provides constraints for deriving atomic structures from such maps. As more deep learning methodologies are being developed for solving various molecular problems, effective tools are needed for users to access them. We have developed an effective software bundle, DeepSSETracer, for the detection of protein secondary structure …

Ssentiaa: A Self-Supervised Sentiment Analyzer For Classification From Unlabeled Data, Salim Sazzed, Sampath Jayarathna

Computer Science Faculty Publications

In recent years, supervised machine learning (ML) methods have realized remarkable performance gains for sentiment classification utilizing labeled data. However, labeled data are usually expensive to obtain, thus, not always achievable. When annotated data are unavailable, the unsupervised tools are exercised, which still lag behind the performance of supervised ML methods by a large margin. Therefore, in this work, we focus on improving the performance of sentiment classification from unlabeled data. We present a self-supervised hybrid methodology SSentiA (Self-supervised Sentiment Analyzer) that couples an ML classifier with a lexicon-based method for sentiment classification from unlabeled data. We first introduce LRSentiA …

Understanding And Predicting Retractions Of Published Work, Sai Ajay Modukuri, Sarah Rajtmajer, Anna Cinzia Squicciarini, Jian Wu, C. Lee Giles

Computer Science Faculty Publications

Recent increases in the number of retractions of published papers reflect heightened attention and increased scrutiny in the scientific process motivated, in part, by the replication crisis. These trends motivate computational tools for understanding and assessment of the scholarly record. Here, we sketch the landscape of retracted papers in the Retraction Watch database, a collection of 19k records of published scholarly articles that have been retracted for various reasons (e.g., plagiarism, data error). Using metadata as well as features derived from full-text for a subset of retracted papers in the social and behavioral sciences, we develop a random forest classifier …

Extractive Research Slide Generation Using Windowed Labeling Ranking, Athar Sefid, Prasenjit Mitra, Jian Wu, C. Lee Giles

Computer Science Faculty Publications

Presentation slides generated from original research papers provide an efficient form to present research innovations. Manually generating presentation slides is labor-intensive. We propose a method to automatically generates slides for scientific articles based on a corpus of 5000 paper-slide pairs compiled from conference proceedings websites. The sentence labeling module of our method is based on SummaRuNNer, a neural sequence model for extractive summarization. Instead of ranking sentences based on semantic similarities in the whole document, our algorithm measures the importance and novelty of sentences by combining semantic and lexical features within a sentence window. Our method outperforms several baseline methods …

Large Scale Subject Category Classification Of Scholarly Papers With Deep Attentive Neural Networks, Bharath Kandimalla, Shaurya Rohatgi, Jian Wu, C. Lee Giles

Computer Science Faculty Publications

Subject categories of scholarly papers generally refer to the knowledge domain(s) to which the papers belong, examples being computer science or physics. Subject category classification is a prerequisite for bibliometric studies, organizing scientific publications for domain knowledge extraction, and facilitating faceted searches for digital library search engines. Unfortunately, many academic papers do not have such information as part of their metadata. Most existing methods for solving this task focus on unsupervised learning that often relies on citation networks. However, a complete list of papers citing the current paper may not be readily available. In particular, new papers that have few …

Multimodal Neuroscience Data Modeling And Inference, Sima Azizi

Doctoral Dissertations

“Mathematical models can be combined with deep learning and machine learning methods to provide new insights in neuroscience. The field of neuroscience is characterized by rich datasets that include fluid biomarkers, EEG signals, and advanced neuroimages. Recent advances in natural language processing have led to the opportunity to gain additional insights from rapidly growing text databases as well as electronic health records. In this research, we focus on applying computational intelligence methods to the analysis of three different complex data sources: blood levels of disease biomarkers, EEG signals from schizophrenic patients, and disease phenotypes encoded in electronic health records. First, …

Binary Black Widow Optimization Algorithm For Feature Selection Problems, Ahmed Al-Saedi

Theses and Dissertations (Comprehensive)

This thesis addresses feature selection (FS) problems, which is a primary stage in data mining. FS is a significant pre-processing stage to enhance the performance of the process with regards to computation cost and accuracy to offer a better comprehension of stored data by removing the unnecessary and irrelevant features from the basic dataset. However, because of the size of the problem, FS is known to be very challenging and has been classified as an NP-hard problem. Traditional methods can only be used to solve small problems. Therefore, metaheuristic algorithms (MAs) are becoming powerful methods for addressing the FS problems. …

Continuity Of Chen-Fliess Series For Applications In System Identification And Machine Learning, Rafael Dahmen, W. Steven Gray, Alexander Schmeding

Electrical & Computer Engineering Faculty Publications

Model continuity plays an important role in applications like system identification, adaptive control, and machine learning. This paper provides sufficient conditions under which input-output systems represented by locally convergent Chen-Fliess series are jointly continuous with respect to their generating series and as operators mapping a ball in an Lp-space to a ball in an Lq-space, where p and q are conjugate exponents. The starting point is to introduce a class of topological vector spaces known as Silva spaces to frame the problem and then to employ the concept of a direct limit to describe convergence. The proof of the main …

The Application Of Machine Learning In Analyzing Organic Compounds From Nmr Spectral Data, Nicole Maia Powell

Senior Independent Study Theses

Nuclear magnetic resonance (NMR) is used in organic chemistry to identify unknown organic compounds. The data obtained from an NMR spectrometer are typically shown in the form of a spectrum, which is then analyzed by an analytical chemist. The action of analyzing a spectrum, especially one of a large and complex molecule, is a long and tedious process. In this project, Python is used to implement hierarchical clustering on NMR data obtained from an NMR spectrometer at the College of Wooster to explore its application in NMR analysis. MATLAB is used to build a decision tree from the same data, …

A Deep Learning U-Net For Detecting And Segmenting Liver Tumors, Vidhya Cardozo

Theses and Dissertations

Visualization of liver tumors on simulation CT scans is challenging even with contrast-enhancement, due to the sensitivity of the contrast enhancement to the timing of the CT acquisition. Image registration to magnetic resonance imaging (MRI) can be helpful for delineation, but differences in patient position, liver shape and volume, and the lack of anatomical landmarks between the two image sets makes the task difficult. This study develops a U-Net based neural network for automated liver and tumor segmentation for purposes of radiotherapy treatment planning. Non-contrast simulation based abdominal CT axial scans of 52 patients with primary liver tumors were utilized. …

Virtual Tutor Personality In Computer Assisted Language Learning, Johanna Dobbriner, Cathy Ennis, Robert J. Ross

Conference papers

The use of intelligent virtual agents in language learning has increased in recent years. Studies into several aspects of personalisation aiming to increase user engagement are an ongoing research topic with avatar personality being one such aspect. As a step towards our development of intelligent virtual avatars, we present two of our initial experiments to explore differences in user interaction with two contrasting avatar personalities -- P1: open-minded, friendly and sociable and P2: closed-off, curt and distant. Each user interacted with a single personality in a video-call setting and gave feedback on the interaction. Our expectations, that P1 would be …

Cybersecurity Leaders: Knowledge Driving Human Capital Development, Sharon L. Burton

Publications

Cybersecurity leaders must be able to use critical reading and thinking skills, exercise judgment when policies are not distinct and precise, and have the knowledge, skills, and abilities to tailor technical and planning data to diverse customers’ levels of understanding. Ninety-three percent of cybersecurity leaders do not report directly to the chief operating officer. While status differences influence interactions amid groups, attackers are smarter. With the aim of protecting organizations and reducing risk, knowledge about security must increase. Understanding voids are costly and increased breach chances are imminent. Burning questions exist. What are needed technological learnings for cybersecurity leaders to …

Implication Of Manifold Assumption In Deep Learning Models For Computer Vision Applications, Marzieh Edraki

Electronic Theses and Dissertations, 2020-2023

The Deep Neural Networks (DNN) have become the main contributor in the field of machine learning (ML). Specifically in the computer vision (CV), there are applications like image and video classification, object detection and tracking, instance segmentation and visual question answering, image and video generation are some of the applications from many that DNNs have demonstrated magnificent progress. To achieve the best performance, the DNNs usually require a large number of labeled samples, and finding the optimal solution for such complex models with millions of parameters is a challenging task. It is known that, the data are not uniformly distributed …

Development Of A Real Time Human Face Recognition Software System, Askar Boranbayev, Seilkhan Boranbayev, Mukhamedzhan Amirtaev, Malik Baimukhamedov, Askar Nurbekov

Physics & Astronomy Faculty Publications

In this study, a system for real-time face recognition was built using the Open Face tools of the Open CV library. The article describes the methodology for creating the system and the results of its testing. The Open CV library has various modules that perform many tasks. In this paper, Open CV modules were used for face recognition in images and face identification in real time. In addition, the HOG method was used to detect a person by the front of his face. After performing the HOG method, 128 face measurements were obtained using the image encoding method. A convolutional …

A Novel Dimensionality Reduction Approach To Improve Microarray Data Classification, Mohammed Hasim, Ismail El Mouden, Mounir Ouzir, Hicham Moutachaouik, Mustapha Hain

Department of Medicine Faculty Publications

Cancer tumor prediction and diagnosis at an early stage has become a necessity in cancer research, as it provides an increase in the treatment success chances. Recently, DNA microarray technology became a powerful tool for cancer identification, that can analyze the expression level of a different and huge number of genes simultaneously. In microarray data, the large genes number versus a few records may affect the prediction performance. In order to handle this "curse of dimensionality” constraint of microarray dataset while improving the cancer identification performance, a dimensional reduction phase is necessary. In this paper, we proposed a framework that …

Artificial Intelligence As Evidence, Paul W. Grimm, Maura R. Grossman, Gordon V. Cormack

Faculty Scholarship

This article explores issues that govern the admissibility of Artificial Intelligence (“AI”) applications in civil and criminal cases, from the perspective of a federal trial judge and two computer scientists, one of whom also is an experienced attorney. It provides a detailed yet intelligible discussion of what AI is and how it works, a history of its development, and a description of the wide variety of functions that it is designed to accomplish, stressing that AI applications are ubiquitous, both in the private and public sectors. Applications today include: health care, education, employment-related decision-making, finance, law enforcement, and the legal …

Ensemble Encoder-Decoder Models For Predicting Land Transformation, Pariya Pourmohammadi

Graduate Theses, Dissertations, and Problem Reports (ETD)

In studying dynamic and complex processes which are influenced by a system of inter-connected driving variables, it is crucial to apply models that can learn the complexity of the interactions. Land transformation is one of such complex processes, prediction of which can help to mitigate severe climate situations and improve the resiliency of communities. In this study, a multi-spectral set of data cubes is used to capture various characteristics of a geographic region. Based on the data cube, a feature space is constructed using socio-economic attributes, terrain characteristics, and landscape traits of the study region. Two-dimensional and three-dimensional convolutional neural …

Association Of Incident Cancer To Low-Value Care And Healthcare Cost Burden Among Elderly Medicare Beneficiaries, Chibuzo Iloabuchi

Graduate Theses, Dissertations, and Problem Reports (ETD)

In the United States (US), 25% of healthcare spending is considered wasteful because it is spent reimbursing low-value care. Low-value care is the utilization of healthcare services, medical tests, and procedures that have unclear or no clinical benefit to patients but still exposes them to risk. World-wide, low-value care imposes a significant economic burden on patients, payers, governments, and society. Cancer care among older adults > 65 years is one of the biggest drivers of healthcare expenditure in the US and accounts for nearly 40% of all spending, and low-value care among cancer patients is prevalent and contributes to the financial …

Deep Fingerprint Matching From Contactless To Contact Fingerprints For Increased Interoperability, Alexander James Wilson

Graduate Theses, Dissertations, and Problem Reports (ETD)

Contactless fingerprint matching is a common form of biometric security today. Most smartphones and associated apps now let users opt into using this form of biometric security. However, it’s difficult to match a finger-photo to a fingerprint because of perspective distortion occurring at the edges of the finger-photo, so direct matching using conventional methods will not be as accurate due to a lack of sufficient matching minutiae points. To address this issue, we propose a deep model, Perspective Distortion Rectification Model (PDRM), to estimate the fingerprint correspondence for finger-photo images in order to recover more minutiae points. Not only do …