Computer Sciences Commons^™

Comparative Analysis Of Hate Speech Detection: Traditional Vs. Deep Learning Approaches, Haibo Pen, Nicole Anne Huiying Teo, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Detecting hate speech on social media poses a significant challenge, especially in distinguishing it from offensive language, as learning-based models often struggle due to nuanced differences between them, which leads to frequent misclassifications of hate speech instances, with most research focusing on refining hate speech detection methods. Thus, this paper seeks to know if traditional learning-based methods should still be used, considering the perceived advantages of deep learning in this domain. This is done by investigating advancements in hate speech detection. It involves the utilization of deep learning-based models for detailed hate speech detection tasks and compares the results with …

Performance Analysis Of Llama 2 Among Other Llms, Donghao Huang, Zhenda Hu, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Llama 2, an open-source large language model developed by Meta, offers a versatile and high-performance solution for natural language processing, boasting a broad scale, competitive dialogue capabilities, and open accessibility for research and development, thus driving innovation in AI applications. Despite these advancements, there remains a limited understanding of the underlying principles and performance of Llama 2 compared with other LLMs. To address this gap, this paper presents a comprehensive evaluation of Llama 2, focusing on its application in in-context learning — an AI design pattern that harnesses pre-trained LLMs for processing confidential and sensitive data. Through a rigorous comparative …

Generative Ai For Pull Request Descriptions: Adoption, Impact, And Developer Interventions, Tao Xiao, Hideaki Hata, Christoph Treude, Kenichi Matsumoto

Research Collection School Of Computing and Information Systems

GitHub's Copilot for Pull Requests (PRs) is a promising service aiming to automate various developer tasks related to PRs, such as generating summaries of changes or providing complete walkthroughs with links to the relevant code. As this innovative technology gains traction in the Open Source Software (OSS) community, it is crucial to examine its early adoption and its impact on the development process. Additionally, it offers a unique opportunity to observe how developers respond when they disagree with the generated content. In our study, we employ a mixed-methods approach, blending quantitative analysis with qualitative insights, to examine 18,256 PRs in …

Jigsaw: Edge-Based Streaming Perception Over Spatially Overlapped Multi-Camera Deployments, Ila Gokarn, Yigong Hu, Tarek Abdelzaher, Archan Misra

Research Collection School Of Computing and Information Systems

We present JIGSAW, a novel system that performs edge-based streaming perception over multiple video streams, while additionally factoring in the redundancy offered by the spatial overlap often exhibited in urban, multi-camera deployments. To assure high streaming throughput, JIGSAW extracts and spatially multiplexes multiple regions-of-interest from different camera frames into a smaller canvas frame. Moreover, to ensure that perception stays abreast of evolving object kinematics, JIGSAW includes a utility-based weighted scheduler to preferentially prioritize and even skip object-specific tiles extracted from an incoming stream of camera frames. Using the CityflowV2 traffic surveillance dataset, we show that JIGSAW can simultaneously process 25 …

Reinforcement Learning For Strategic Airport Slot Scheduling: Analysis Of State Observations And Reward Designs, Anh Nguyen-Duy, Duc-Thinh Pham, Jian-Yi Lye, Nguyen Binh Duong Ta

Research Collection School Of Computing and Information Systems

Due to the NP-hard nature, the strategic airport slot scheduling problem is calling for exploring sub-optimal approaches, such as heuristics and learning-based approaches. Moreover, the continuous increase in air traffic demand requires approaches that can work well in new scenarios. While heuristics rely on a fixed set of rules, which limits the ability to explore new solutions, Reinforcement Learning offers a versatile framework to automate the search and generalize to unseen scenarios. Finding a suitable state observation and reward structure design is essential in using Reinforcement Learning. In this paper, we investigate the impact of providing the Reinforcement Learning agent …

Learning Topological Representations With Bidirectional Graph Attention Network For Solving Job Shop Scheduling Problem, Cong Zhang, Zhiguang Cao, Yaoxin Wu, Wen Song, Jing Sun

Research Collection School Of Computing and Information Systems

Existing learning-based methods for solving job shop scheduling problems (JSSP) usually use off-the-shelf GNN models tailored to undirected graphs and neglect the rich and meaningful topological structures of disjunctive graphs (DGs). This paper proposes the topology-aware bidirectional graph attention network (TBGAT), a novel GNN architecture based on the attention mechanism, to embed the DG for solving JSSP in a local search framework. Specifically, TBGAT embeds the DG from a forward and a backward view, respectively, where the messages are propagated by following the different topologies of the views and aggregated via graph attention. Then, we propose a novel operator based …

Configurable Mirror Descent : Towards A Unification Of Decision Making, Pengdeng Li, Shuxin Li, Chang Yang, Xinrun Wang, Hau Chan, Bo An

Research Collection School Of Computing and Information Systems

Decision-making problems, categorized as single-agent, e.g., Atari, cooperative multi-agent, e.g., Hanabi, competitive multi-agent, e.g., Hold’em poker, and mixed cooperative and competitive, e.g., football, are ubiquitous in the real world. Although various methods have been proposed to address the specific decision-making categories, these methods typically evolve independently and cannot generalize to other categories. Therefore, a fundamental question for decision-making is: Can we develop a single algorithm to tackle ALL categories of decision-making problems? There are several main challenges to address this question: i) different decision-making categories involve different numbers of agents and different relationships between agents, ii) different categories have different …

Topic Modeling On Document Networks With Dirichlet Optimal Transport Barycenter (Extended Abstract), Ce Zhang, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Texts are often interconnected in a network structure, e.g., academic papers via citations. On the one hand, though Graph Neural Networks (GNNs) have shown promising ability to derive effective embeddings for networked documents, they do not assume latent topics, resulting in uninterpretahle embeddings. On the other hand, topic models can infer interpretable document representations. However, most topic models focus on plain text and fail to leverage network structure across documents. In this paper, we propose a GNN-based topic model that both captures network connection and derives semantically interpretable text representations. For network modeling, we build our model with Optimal Transport …

Augmenting Decision With Hypothesis In Reinforcement Learning, Minh Quang Nguyen, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Value-based reinforcement learning is the current State-Of-The-Art due to high sampling efficiency. However, our study shows it suffers from low exploitation in early training period and bias sensitiveness. To address these issues, we propose to augment the decision-making process with hypothesis, a weak form of environment description. Our approach relies on prompting the learning agent with accurate hypotheses, and designing a ready-to-adapt policy through incremental learning. We propose the ALH algorithm, showing detailed analyses on a typical learning scheme and a diverse set of Mujoco benchmarks. Our algorithm produces a significant improvement over value-based learning algorithms and other strong baselines. …

Unified Training Of Universal Time Series Forecasting Transformers, Gerald Woo, Chenghao Liu, Akshat Kumar, Caiming Xiong, Silvio Savarese, Doyen Sahoo

Research Collection School Of Computing and Information Systems

Deep learning for time series forecasting has traditionally operated within a one-model-per-dataset framework, limiting its potential to leverage the game-changing impact of large pre-trained models. The concept of universal forecasting, emerging from pre-training on a vast collection of time series datasets, envisions a single Large Time Series Model capable of addressing diverse downstream forecasting tasks. However, constructing such a model poses unique challenges specific to time series data: i) cross-frequency learning, ii) accommodating an arbitrary number of variates for multivariate time series, and iii) addressing the varying distributional properties inherent in large-scale data. To address these challenges, we present novel …

Diffusion Models For Generative Outfit Recommendation, Yiyan Xu, Wenjie Wang, Fuli Feng, Yunshan Ma, Jizhi Zhang, Xiangnan He

Research Collection School Of Computing and Information Systems

Outfit Recommendation (OR) in the fashion domain has evolved through two stages: Pre-defined Outfit Recommendation and Personalized Outfit Composition. However, both stages are constrained by existing fashion products, limiting their effectiveness in addressing users' diverse fashion needs. Recently, the advent of AI-generated content provides the opportunity for OR to transcend these limitations, showcasing the potential for personalized outfit generation and recommendation.To this end, we introduce a novel task called Generative Outfit Recommendation (GOR), aiming to generate a set of fashion images and compose them into a visually compatible outfit tailored to specific users. The key objectives of GOR lie in …

Adaptive Stabilization Based On Machine Learning For Column Generation, Yunzhuang Shen, Yuan Sun, Xiaodong Li, Zhiguang Cao, Eberhard Andrew, Guangquan Zhang

Research Collection School Of Computing and Information Systems

Column generation (CG) is a well-established method for solving large-scale linear programs. It involves iteratively optimizing a subproblem containing a subset of columns and using its dual solution to generate new columns with negative reduced costs. This process continues until the dual values converge to the optimal dual solution to the original problem. A natural phenomenon in CG is the heavy oscillation of the dual values during iterations, which can lead to a substantial slowdown in the convergence rate. Stabilization techniques are devised to accelerate the convergence of dual values by using information beyond the state of the current subproblem. …

Mvmoe: Multi-Task Vehicle Routing Solver With Mixture-Of-Experts, Jianan Zhou, Zhiguang Cao, Yaoxin Wu, Wen Song, Yining Ma, Jie Zhang, Chi Xu

Research Collection School Of Computing and Information Systems

Learning to solve vehicle routing problems (VRPs) has garnered much attention. However, most neural solvers are only structured and trained independently on a specific problem, making them less generic and practical. In this paper, we aim to develop a unified neural solver that can cope with a range of VRP variants simultaneously. Specifically, we propose a multi-task vehicle routing solver with mixture-of-experts (MVMoE), which greatly enhances the model capacity without a proportional increase in computation. We further develop a hierarchical gating mechanism for the MVMoE, delivering a good trade-off between empirical performance and computational complexity. Experimentally, our method significantly promotes …

Is There A Space In Landslide Susceptibility Modelling: A Case Study Of Valtellina Valley, Northern Italy, Min Naing Khant, Mei Yi Victoria Grace Ann, Tin Seong Kam

Research Collection School Of Computing and Information Systems

Landslides pose significant and ever-threatening risks to human life and infrastructure worldwide. Landslide susceptibility modelling is an emerging field of research seeking to determine contributing factors of these events. Yet, previous studies rarely explored the spatial variation of different landslide factors. Hence, this study aims to demonstrate the potential contribution of spatial nonstationarity in landslide susceptibility modelling using Global Logistic Regression (GLR) and Geographically Weighted Logistic Regression (GWLR). The second objective of this study is to demonstrate the important role of data preparation, data sampling, variable sensing, and variable selections in landslide susceptibility modelling. Using Valtellina Valley in Northern Italy …

The Information Content Of Financial Statement Fraud Risk: An Ensemble Learning Approach, Wei Duan, Nan Hu, Fujing Xue

Research Collection School Of Computing and Information Systems

This study aims to assess the financial statement fraud risk ex ante and empirically explore its information content to help improve decision-making and daily operations. We propose an ex-ante fraud risk index by adopting an ensemble learning approach and a theoretically grounded framework. Our ensemble learning model systematically examines the fraud process and deals effectively with the unique challenges in the financial fraud setting, which yields superior prediction performance. More importantly, we empirically examine the information content of our estimated ex-ante fraud risk from the perspective of operational efficiency. Our empirical results find that the estimated ex-ante fraud risk is …

Generative Artificial Intelligence: The Protection Of Personal Data And Countering False Narratives About The Person, Warren B. Chik

Research Collection Yong Pung How School Of Law

Generative artificial intelligence (“Gen AI”) has rapidly become ubiquitous on online platform services, from chatbots and virtual assistants to search engines and social media. This generated concerns over potentially harmful effects from its use in both social and professional settings, including the added threats to personal data privacy and accuracy of personal information. In this article, the author will explain how Gen AI operates and why it gives rise to these issues, examine the policy and law relating to Gen AI, both existent and anticipated, and suggest possible solutions to the problems in the form of legal and non-legal measures.

Empowering Interprofessional Teams: Exploring Genai With The Health Sciences Library, Jess King, Teresa L. Hartman

Posters and Presentations: Leon S. McGoogan Health Sciences Library

The Leon S. McGoogan Health Sciences Library at the University of Nebraska Medical Center (UNMC) organized workshops to delve into Generative Artificial Intelligence (GenAI) applications in academic medical centers. These sessions, tailored for all skill levels, provided a safe forum for faculty and staff to engage with GenAI, increasing their digital literacy skills. Participants benefited from introductory sessions, hands-on activities, and reflective discussions, gaining practical insights into ethical GenAI use. These workshops form a vibrant GenAI community at UNMC, fostering collaboration and knowledge exchange among healthcare professionals and paving the way for continued technological integration in academic and clinical settings

Who Wrote The Scientific News? Improving The Discernibility Of Llms To Human-Written Scientific News, Dominik Soós

Computer Science Theses & Dissertations

Large Language Models (LLMs) have rapidly advanced the field of Natural Language Processing and become powerful tools for generating and evaluating scientific text. Although LLMs have demonstrated promising as evaluators for certain text generation tasks, there is still a gap until they are used as reliable text evaluators for general purposes. In this thesis project, I attempted to fill this gap by examining the discernibility of LLMs from human-written and LLM-generated scientific news. This research demonstrated that although it was relatively straightforward for humans to discern scientific news written by humans from scientific news generated by GPT-3.5 using basic prompts, …

Explainable Artificial Intelligence: Methods And Evaluation, Gayane Grigoryan

Engineering Management & Systems Engineering Theses & Dissertations

A wide array of techniques within explainable artificial intelligence (XAI) have been developed to measure the importance of features in machine learning models. A notable portion of these methods draws upon principles of cooperative game theory (CGT), with the Shapley value emerging as a widely used solution concept. Despite the rising prominence of the Shapley value, other promising solutions from cooperative game theory—such as the Nucleolus, Banzhaf power index, Shapley-Shubik power index, and solutions to conflicting claims problems—have been comparatively overlooked, even though they hold significant potential. In this dissertation, multiple XAI methods based on these other CGT solutions are …

Privacy-Preserving Deep Learning Framework For Iot Malware Detection, Sabbir Ahmed Khan

Computer Science Theses & Dissertations

Cyberattacks on IoT devices are accelerating at an unprecedented rate, largely driven by IoT malware activities. The IoT malware attacks typically comprise three stages: intrusion, infection, and monetization. Existing IoT malware detection methods fail to identify malicious activities at the intrusion and infection stages and thus cannot stop potential attacks timely. In our research, we have leveraged power side-channel information as input to our deep learning model to identify malware at early stages of intrusion on IoT devices. But, deploying a resource-intensive deep learning model on highly resource-constrained IoT devices is a significant challenge. Consequently, utilizing a Machine Learning as …

Mesostructure Reconstruction Of Prepreg Platelet Molded Composite With Artificial Intelligence, Richard Larson

Mechanical & Aerospace Engineering Theses & Dissertations

Prepreg platelet molded composites (PPMC) are long, discontinuous fiber reinforced polymer materials. PPMC are an important subcategory of composite materials as they are processible into geometrically complex structures and can be produced via high-throughput manufacturing processes, however they have higher stiffness and strength as compared to traditional discontinuous fiber reinforced polymers. However, there is inherent randomness in the structure of PPMCs and as such, PPMC parts frequently require per part testing that is cost prohibitive.

Herein, a method using artificial intelligence is proposed as a more cost-effective method of inspecting PPMC parts. Different artificial intelligence (AI) architectures are explored to …

Deep Learning In Reproducing Kernel Banach Spaces, Mingsong Yan

Mathematics & Statistics Theses & Dissertations

Deep learning has achieved immense success in the past decade. The goal of this dissertation is to understand deep learning through the framework of reproducing kernel Banach spaces (RKBSs), which were originally proposed for promoting sparse solutions. We begin by considering learning problems in a general functional setting, and establishing explicit and data-dependent representer theorems for both minimal norm interpolation (MNI) problems and regularization problems. These theorems provide a crucial foundation for the subsequent results derived for both sparse learning and deep learning. Next, we investigate the essential properties of RKBSs capable of encouraging sparsity in learning solutions. With the …

Harnessing Social Media For Disaster Response: Intelligent Identification Of Reliable Rescue Requests During Hurricanes, Wael Khallouli

Engineering Management & Systems Engineering Theses & Dissertations

Hurricanes pose a significant threat to both human lives and infrastructure. Decision-makers face substantial challenges during such events, as they must act quickly to address victims’ needs. Social media platforms provide a valuable source for quick and real-time information. Recent hurricane events have shown that people turn to social media to call for help when official communication channels, such as 911, are overwhelmed. However, extracting actionable information from the massive number of messages posted on social media is challenging. Furthermore, verifying social media messages posted by the public is a critical concern for disaster response practitioners, making them hesitant to …

Enhancing Tumor Classification Through Machine Learning Algorithms For Breast Cancer Diagnosis, Lawrence Agbota, Edmund F. Agyemang, Priscilla Kissi-Appiah, Lateef Moshood, Akua Osei- Nkwantabisa, Vincent Agbenyeavu, Abraham Nsiah, Augustina Adjei

School of Mathematical & Statistical Sciences Faculty Publications

In cancer diagnosis, machine learning helps improve cancer detection by providing doctors with a second perspective and allowing for faster and more accurate determination and decisions. Numerous studies have used both classic machine learning approaches and deep learning to address cancer classification. In this study, we examine the efficacy of five commonly used machine learning algorithms; both traditional and deep learning models namely, Logistic Regression, Support Vector Machines (SVM), Random Forest (RF), Decision Tree and Deep Neural Networks (DNN). We analyze their ability to properly classify tumors as Benign or Malignant using the Wisconsin breast cancer dataset (WBCD). Random Forest …

Containerization On A Self-Supervised Active Foveated Approach To Computer Vision, Dario Dematties, Silvio Rizzi, George K. Thiruvathukal

Computer Science: Faculty Publications and Other Works

Scaling complexity and appropriate data sets availability for training current Computer Vision (CV) applications poses major challenges. We tackle these challenges finding inspiration in biology and introducing a Self-supervised (SS) active foveated approach for CV. In this paper we present our solution to achieve portability and reproducibility by means of containerization utilizing Singularity. We also show the parallelization scheme used to run our models on ThetaGPU–an Argonne Leadership Computing Facility (ALCF) machine of 24 NVIDIA DGX A100 nodes. We describe how to use mpi4py to provide DistributedDataParallel (DDP) with all the needed information about world size as well as global …

Student Partners In Ai Literacy: A Library And Writing Center Collaboration, A. P. Anderson

Velma K. Waters Library Faculty Publications

Student voices are valuable but often overlooked in discussions surrounding the role of AI in higher education. AI Literacy education efforts that treat students only as a potential audience for instruction rather than as potential instructors themselves miss out on the passion, curiosity, and complex questions that students can bring to these conversations. If we center student voices in AI Literacy education discussions, and encourage both their enthusiasm and skepticism, students can become comfortable and confident in leading discussions about AI in the classroom and in their lives. In my proposed poster presentation, I will share insights from an AI …

Ai Literacy Innovations: Chatgpt's Integration Into A First-Year Information Literacy Program, Taylor J. Greene, Douglas R. Dechow

Library Presentations, Posters, and Audiovisual Materials

In the dynamic field of information technology, integration of Artificial Intelligence (AI) literacy into information literacy instruction is now essential to ensure the ethical and productive use of generative AI by our students. This poster demonstrates our innovative approach to embedding AI literacy within the first-year information literacy program at an R2 research university. We used a two-pronged strategy: an “AI Literacy” section in Canvas and practical demonstrations of applying ChatGPT in live library sessions. The Canvas module section equips students with foundational knowledge and critical thinking about using generative AI for research and learning activities. It covers AI fundamentals, …

Hyper-Dimensional Computing And Its Applications In Tinyml, Ellis A. Weglewski

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

As computing systems enter the realm of nano form levels, new fields of computational development have spawned, each posing their own set of challenges. Amongst these fields is Tiny Machine Learning (tinyML), which aims to install machine learning on tiny embedded systems. The restrictions imposed upon algorithms by the limited hardware of nano-scale tiny systems make contemporary approaches to machine learning non-contenders. Hyperdimensional computing is an approach to representing data as high-dimensional vectors which allows for one-pass encoding and quick all-encompassing comparison operations via an associative memory. This approach is power-efficient, robust, and can be done in-memory, all of which …

Simulation Of Rice Disease Recognition Based On Improved Attention Mechanism Embedded In Pr-Net Model, Yang Lu, Pengfei Liu, Siyuan Xu, Qiwang Liu, Fuqian Gu, Peng Wang

Journal of System Simulation

Abstract: Aiming at the low accuracy of existing CNN models in identifying rice leaf diseases, a hybrid convolutional neural network model PRC-Net (parallel residual with coordinate attention network) combining parallel structure and residual structure is proposed. A parallel structure is introduced to improve the receptive field of convolution, and the residual structure is combined to achieve the complete and continuous transmission of feature information. An improved spatial attention mechanism is embedded into the backbone model PR-Net to enhance the degree of aggregation of lesion feature information at different scales. In order to further improve the accuracy of disease identification and …

Just-In-Time Learning Energy Consumption Predictive Modeling Method In Multi-Condition Production Process, Sheng Wei, Yan Wang, Zhicheng Ji

Journal of System Simulation

Abstract: Aiming at the problem that the global energy consumption prediction model is only suitable for part of the prediction sample and the model is computationally intensive, the idea of just-in-time learning is introduced, and the local weighted partial least squares method combined with the energy consumption model is used to establish a temporary local energy consumption prediction model. The inertia weights of the particle swarm algorithm are improved, considering the effects of particle fitness, number of iterations and population size on the convergence speed and convergence accuracy of the particle swarm algorithm, a nonlinear change adaptive inertia weight strategy …