Physical Sciences and Mathematics Commons^™

Ai-Powered Learning: Blending Ai With Active Learning In The Information Literacy Classroom, Kevin J. Reagan, Wilhelmina Randtke

Georgia International Conference on Information Literacy

In 2016, the ACRL Framework for Information Literacy in Higher Education launched in response to more voluminous, less-vetted online information, including misinformation and content farms. Subsequently, the ACRL Framework has been widely adopted, and numerous high-quality lesson plans and resources for teaching the frames already exist, including published lesson plans and textbooks. Now, generative AI tools, such as ChatGPT and other chat bots present new challenges for information literacy educators. For instance, in addition to teaching students how to identify issues such as fake news, the information literacy professional has to address topics such as ethical AI use, AI hallucination …

Active Code Learning: Benchmarking Sample-Efficient Training Of Code Models, Qiang Hu, Yuejun Guo, Xiaofei Xie, Maxime Cordy, Lei Ma, Mike Papadakis, Yves Le Traon

Research Collection School Of Computing and Information Systems

The costly human effort required to prepare the training data of machine learning (ML) models hinders their practical development and usage in software engineering (ML4Code), especially for those with limited budgets. Therefore, efficiently training models of code with less human effort has become an emergent problem. Active learning is such a technique to address this issue that allows developers to train a model with reduced data while producing models with desired performance, which has been well studied in computer vision and natural language processing domains. Unfortunately, there is no such work that explores the effectiveness of active learning for code …

Real: A Representative Error-Driven Approach For Active Learning, Cheng Chen, Yong Wang, Lizi Liao, Yueguo Chen, Xiaoyong Du

Research Collection School Of Computing and Information Systems

Given a limited labeling budget, active learning (al) aims to sample the most informative instances from an unlabeled pool to acquire labels for subsequent model training. To achieve this, al typically measures the informativeness of unlabeled instances based on uncertainty and diversity. However, it does not consider erroneous instances with their neighborhood error density, which have great potential to improve the model performance. To address this limitation, we propose Real, a novel approach to select data instances with Representative Errors for Active Learning. It identifies minority predictions as pseudo errors within a cluster and allocates an adaptive sampling budget for …

Mentoring Deep Learning Models For Mass Screening With Limited Data, Suprim Nakarmi

Dissertations and Theses

Deep Learning (DL) has an extensively rich state-of-the-art literature in medical imaging analysis. However, it requires large amount of data to begin training. This limits its usage in tackling future epidemics, as one might need to wait for months and even years to collect fully annotated data, raising a fundamental question: is it possible to deploy AI-driven tool earlier in epidemics to mass screen the infected cases? For such a context, human/Expert in the loop Machine Learning (ML), or Active Learning (AL), becomes imperative enabling machines to commence learning from the first day with minimum available labeled dataset. In an …

Deep Active Genetic Learning With Evidential Uncertainty For Agriculture Crops And Lake Water Quality Assessment, Oguz M. Aranay

Legacy Theses & Dissertations (2009 - 2024)

Despite significant advancements in the field of machine learning, there are two issues that still require further exploration. First, how to learn from a small dataset; and second, how to select appropriate features from the data. Although there exist many techniques to address these issues, choosing a combination of the techniques from these two groups is challenging, and worth investigating. To address these concerns, this thesis presents a learning framework that is based on a deep learning model utilizing active learning (with evidential uncertainty as a basis for acquisition function) for the first issue and a genetic algorithm for the …

Active Learning With Cybersecurity, Carole Shook

TFSC Publications and Presentations

A global campus grant was obtained in Spring 2020 to develop modules for Cybersecurity. This presentation encompasses the use of Cyberciege and case studies that require active learning of students.

Active Learning Of Discriminative Subgraph Patterns For Api Misuse Detection, Hong Jin Kang, David Lo

Research Collection School Of Computing and Information Systems

A common cause of bugs and vulnerabilities are the violations of usage constraints associated with Application Programming Interfaces (APIs). API misuses are common in software projects, and while there have been techniques proposed to detect such misuses, studies have shown that they fail to reliably detect misuses while reporting many false positives. One limitation of prior work is the inability to reliably identify correct patterns of usage. Many approaches confuse a usage pattern’s frequency for correctness. Due to the variety of alternative usage patterns that may be uncommon but correct, anomaly detection-based techniques have limited success in identifying misuses. We …

Active Learning Augmented Folded Gaussian Model For Anomaly Detection In Smart Transportation, Venkata Praveen Kumar Madhavarapu, Prithwiraj Roy, Shameek Bhattacharjee, Sajal K. Das

Computer Science Faculty Research & Creative Works

Smart transportation networks have become instrumental in smart city applications with the potential to enhance road safety, improve the traffic management system and driving experience. A Traffic Message Channel (TMC) is an IoT device that records the data collected from the vehicles and forwards it to the Roadside Units (RSUs). This data is further processed and shared with the vehicles to inquire the fastest route and incidents that can cause significant delays. The failure of the TMC sensors can have adverse effects on the transportation network. In this paper, we propose a Gaussian distribution-based trust scoring model to identify anomalous …

Bayesian Quadrature With Prior Information: Modeling And Policies, Henry Chai

McKelvey School of Engineering Theses & Dissertations

Quadrature is the problem of estimating intractable integrals. Such integrals regularly arise in engineering and the natural sciences, especially when Bayesian methods are applied; examples include model evidences, normalizing constants and marginal distributions. This dissertation explores Bayesian quadrature, a probabilistic, model-based quadrature method. Specifically, we study different ways in which Bayesian quadrature can be adapted to account for different kinds of prior information one may have about the task. We demonstrate that by taking into account prior knowledge, Bayesian quadrature can outperform commonly used numerical methods that are agnostic to prior knowledge, such as Monte Carlo based integration. We focus …

The U-Net-Based Active Learning Framework For Enhancing Cancer Immunotherapy, Vishwanshi Joshi

Theses, Dissertations and Capstones

Breast cancer is the most common cancer in the world. According to the U.S. Breast Cancer Statistics, about 281,000 new cases of invasive breast cancer are expected to be diagnosed in 2021 (Smith et al., 2019). The death rate of breast cancer is higher than any other cancer type. Early detection and treatment of breast cancer have been challenging over the last few decades. Meanwhile, deep learning algorithms using Convolutional Neural Networks to segment images have achieved considerable success in recent years. These algorithms have continued to assist in exploring the quantitative measurement of cancer cells in the tumor microenvironment. …

Transitioning To An Active Learning Environment For Calculus At The University Of Florida, Darryl Chamberlain, Amy Grady, Scott Keeran, Kevin Knudson, Ian Manly, Melissa Shabazz, Corey Stone

Publications

In this note, we describe a large-scale transition to an active learning format in first-semester calculus at the University of Florida. Student performance and attitudes are compared across traditional lecture and flipped sections.

Tactivities: Fostering Creativity Through Tactile Learning Activities, Angie Hodge-Zickerman, Eric Stade, Cindy S. York, Janice Rech

Journal of Humanistic Mathematics

As mathematics teachers, we hope our students will approach problems with a spirit of creativity. One way to both model and encourage this spirit – and, at the same time, to keep ourselves from getting bored – is through creative approaches to problem design. In this paper, we discuss ``TACTivities'' – mathematical activities with a tactile component – as a creative outlet for those of us who teach mathematics, and as a resource for stimulating creative thinking in our students. We use examples, such as our ``derivative fridge magnets'' TACTivity, to illustrate the main ideas. We emphasize that TACTivities can …

Active Deep Learning Method To Automate Unbiased Stereology Cell Counting, Saeed Alahmari

USF Tampa Graduate Theses and Dissertations

Cell quantification in histopathology images plays a significant role in understanding and diagnosing diseases such as cancer and Alzheimers. The gold-standard for quantifying cells in tissue sections is the unbiased stereology approach. Unfortunately, in unbiased stereology current practices rely on a well-trained human to manually count hundreds of cells in microscopy images. However, this human-based manual approach is time-consuming, labor-intensive, subject to human errors, recognition bias, fatigue, variable training, poor reproducibility, and inter-observer error. Thus, the lack of high-throughput technology for automating unbiased stereology analyses remains a major obstacle to further progress in a wide range of neuroscience and cancer …

Everyone Loves Gummi Bears! Removing The Intimidation Factor From Research Data Management With Yummy Fun., Dawn N. Cannon-Rech, Jeffrey M. Mortimore

Georgia International Conference on Information Literacy

How do you get students excited about research data management and attract over 70 participants to a voluntary workshop? How do you get Librarians excited about teaching a research data management workshop to undergraduates? With the promise of Gummi Bears and hands-on fun! During this workshop session, presenters will break down their experience overhauling a faculty workshop into an active learning session to expose students of all experience levels to basic research data management concepts and techniques. Presenters will walk participants through their design process from inception to delivery, highlighting how Gummi Bears lessened students’ intimidation with this complex topic …

Attention Mechanism In Deep Neural Networks For Computer Vision Tasks, Haohan Li

Doctoral Dissertations

“Attention mechanism, which is one of the most important algorithms in the deep Learning community, was initially designed in the natural language processing for enhancing the feature representation of key sentence fragments over the context. In recent years, the attention mechanism has been widely adopted in solving computer vision tasks by guiding deep neural networks (DNNs) to focus on specific image features for better understanding the semantic information of the image. However, the attention mechanism is not only capable of helping DNNs understand semantics, but also useful for the feature fusion, visual cue discovering, and temporal information selection, which are …

Machine Learning Methods For Personalized Health Monitoring Using Wearable Sensors, Annamalai Natarajan

Doctoral Dissertations

Mobile health is an emerging field that allows for real-time monitoring of individuals between routine clinical visits. Among others it makes it possible to remotely gather health signals, track disease progression and provide just-in-time interventions. Consumer grade wearable sensors can remotely gather health signals and other time series data. While wearable sensors can be readily deployed on individuals, there are significant challenges in converting raw sensor data into actionable insights. In this dissertation, we develop machine learning methods and models for personalized health monitoring using wearables. Specifically, we address three challenges that arise in these settings. First, data gathered from …

Knowledge-Enabled Entity Extraction, Hussein S. Al-Olimat

Browse all Theses and Dissertations

Information Extraction (IE) techniques are developed to extract entities, relationships, and other detailed information from unstructured text. The majority of the methods in the literature focus on designing supervised machine learning techniques, which are not very practical due to the high cost of obtaining annotations and the difficulty in creating high quality (in terms of reliability and coverage) gold standard. Therefore, semi-supervised and distantly-supervised techniques are getting more traction lately to overcome some of the challenges, such as bootstrapping the learning quickly. This dissertation focuses on information extraction, and in particular entities, i.e., Named Entity Recognition (NER), from multiple domains, …

From Rankings To Ratings: Rank Scoring Via Active Learning, Jack O'Neill, Sarah Jane Delany, Brian Mac Namee

Conference papers

In this paper we present RaScAL, an active learning approach to predicting real-valued scores for items given access to an oracle and knowledge of the overall item-ranking. In an experiment on six different datasets, we find that RaScAL consistently outperforms the state-of-the-art. The RaScAL algorithm represents one step within a proposed overall system of preference elicitations of scores via pairwise comparisons.

Second-Order Online Active Learning And Its Applications, Shuji Hao, Jing Lu, Peilin Zhao, Chi Zhang, Steven C. H. Hoi, Chunyan Miao

Research Collection School Of Computing and Information Systems

The goal of online active learning is to learn predictive models from a sequence of unlabeled data given limited label querybudget. Unlike conventional online learning tasks, online active learning is considerably more challenging because of two reasons.Firstly, it is difficult to design an effective query strategy to decide when is appropriate to query the label of an incoming instance givenlimited query budget. Secondly, it is also challenging to decide how to update the predictive models effectively whenever the true labelof an instance is queried. Most existing approaches for online active learning are often based on a family of first-order online …

New Explainable Active Learning Approach For Recommender Systems, Sami Khenissi, Behnoush Abdollahi, Wenlong Sun, Pegah Sagheb, Olfa Nasraoui

Commonwealth Computational Summit

Introduction and Motivations

• Recommender Systems are intelligent programs that analyze patterns between items and users to predict the user’s taste.

Objective

• Design an efficient Active Learning Strategy to increase the explainability and the accuracy of an “Explainable Matrix Factorization” model.

Panel: Teaching To Increase Diversity And Equity In Stem, Helen H. Hu, Douglas Blank, Albert Chan, Travis E. Doom

Computer Science and Engineering Faculty Publications

TIDES (Teaching to Increase Diversity and Equity in STEM) is a three-year initiative to transform colleges and universities by changing what STEM faculty, especially CS instructors, are doing in the classroom to encourage the success of their students, particularly those that have been traditionally underrepresented in computer science.Each of the twenty projects selected proposed new inter-disciplinary curricula and adopted culturally sensitive pedagogies, with an eye towards departmental and institutional change. The four panelists will each speak about their TIDES projects, which all involved educating faculty about cultural competency. Three of the panelists infused introductory CS courses with applications from other …

Role Of Students’ Participation On Learning Physics In Active Learning Classes, Binod Nainabasti

FIU Electronic Theses and Dissertations

Students’ interactions can be an influential component of students’ success in an interactive learning environment. From a participation perspective, learning is viewed in terms of how students transform their participation. However, many of the seminal papers discussing the participationist framework are vague on specific details about what student participation really looks like on a fine-grained scale. As part of a large project to understand the role of student participation in learning, this study gathered data that quantified students’ participation in three broad areas of two student-centered introductory calculus-based physics classes structured around the Investigative Science Learning Environment (ISLE) philosophy. These …

Instructional Framing And Student Learning Of Community Interactions, Nathaniel Niosco

School of Natural Resources: Dissertations, Theses, and Student Research

Ecology is a broad field of science that encompasses many disciplines with large impacts in our society (AAAS, 2011; NRC, 2009). To understand the complex systems and concepts of this discipline requires a foundation of knowledge that students often gain in the classroom (Bransford, Brown, & Cocking, 2000). Helping students develop this foundation of knowledge requires an understanding of how they use surface and deep reasoning skills to understand and learn new material. In addition, using methods to teach students to transfer these skills between multiple contexts is key to expanding their ability to broadly apply knowledge. The purpose of …

Increment - Interactive Cluster Refinement, Logan Adam Mitchell

Theses and Dissertations

We present INCREMENT, a cluster refinement algorithm which utilizes user feedback to refine clusterings. INCREMENT is capable of improving clusterings produced by arbitrary clustering algorithms. The initial clustering provided is first sub-clustered to improve query efficiency. A small set of select instances from each of these sub-clusters are presented to a user for labelling. Utilizing the user feedback, INCREMENT trains a feature embedder to map the input features to a new feature space. This space is learned such that spatial distance is inversely correlated with semantic similarity, determined from the user feedback. A final clustering is then formed in the …

Active Crowdsourcing For Annotation, Shuji Hao, Chunyan Miao, Steven C. H. Hoi, Peilin Zhao

Research Collection School Of Computing and Information Systems

Crowdsourcing has shown great potential in obtaining large-scale and cheap labels for different tasks. However, obtaining reliable labels is challenging due to several reasons, such as noisy annotators, limited budget and so on. The state-of-the-art approaches, either suffer in some noisy scenarios, or rely on unlimited resources to acquire reliable labels. In this article, we adopt the learning with expert~(AKA worker in crowdsourcing) advice framework to robustly infer accurate labels by considering the reliability of each worker. However, in order to accurately predict the reliability of each worker, traditional learning with expert advice will consult with external oracles~(AKA domain experts) …

Community Structure In Introductory Physics Course Networks, Adrienne L. Traxler

Physics Faculty Publications

Student-to-student interactions are foundational to many active learning environments, but are most often studied using qualitative methods. Quantitative network analysis tools complement this picture, allowing researchers to describe the social interactions of whole classrooms as systems. Past results in introductory physics have suggested a sharp division in the formation of social structure between large lecture sections and small studio classroom environments. Extending those results, this study focuses on calculus-based introductory physics courses at a large public university with a heavily commuter and nontraditional student population. Community detection network methods are used to characterize pre- and post-course collaborative structure in several …

Change At The Core: An Initial Implementation Of Active Learning Strategies In Large, Lecture Science Courses, Travis Salmi

Scholars Week

Change at the Core (C-Core) is a faculty professional development program designed to investigate and employ the benefits of student focused learning in introductory science courses. It is a multidisciplinary effort among science educators at three higher education institutions to understand different possible learning strategy implementations. We are using case studies to investigate these implementations, the challenges involved, and the student responses to these approaches. Previous research has shown that students respond with greater learning outcomes towards alternatives to lectures. Data are being collected through classroom observations, student surveys, and faculty interviews. So far, we have observed a range of …

Probing The Inverted Classroom: A Study Of Teaching And Learning Outcomes In Engineering And Mathematics, Nancy K. Lape, Rachel Levy, Darryl Yong

All HMC Faculty Publications and Research

Flipped classrooms have started to become commonplace on university campuses. Despite the growing number of flipped courses, however, quantitative information on their effectiveness remains sparse. Active learning is a mode of instruction that focuses the responsibility of learning on learners. Multiple studies have shown that active learning leads to better student outcomes. Given that instructors in flipped classrooms are generally able to create more opportunities for students to apply or practice course material, we hypothesized that students in a flipped classroom would exhibit more learning compared to students in an unflipped class. This case study describes our research comparing …

Online Passive Aggressive Active Learning And Its Applications, Jing Lu, Peilin Zhao, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

We investigate online active learning techniques for classification tasks in data stream mining applications. Unlike traditional learning approaches (either batch or online learning) that often require to request the class label of each incoming instance, online active learning queries only a subset of informative incoming instances to update the classification model, which aims to maximize classification performance using minimal human labeling effort during the entire online stream data mining task. In this paper, we present a new family of algorithms for online active learning called Passive-Aggressive Active (PAA) learning algorithms by adapting the popular Passive-Aggressive algorithms in an online active …

Active Code Search: Incorporating User Feedback To Improve Code Search Relevance, Shaowei Wang, David Lo, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Code search techniques return relevant code fragments given a user query. They typically work in a passive mode: given a user query, a static list of code fragments sorted by the relevance scores decided by a code search technique is returned to the user. A user will go through the sorted list of returned code fragments from top to bottom. As the user checks each code fragment one by one, he or she will naturally form an opinion about the true relevance of the code fragment. In an active model, those opinions will be taken as feedbacks to the search …