Digital Commons Network^™

Gtree: Gpu-Friendly Privacy-Preserving Decision Tree Training And Inference, Qifan Wang, Shujie Cui, Lei Zhou, Ye Dong, Jianli Bai, Yun Sing Koh, Giovanni Russello

Research Collection School Of Computing and Information Systems

Outsourcing Decision tree (DT) training and inference to cloud platforms raises privacy concerns. Recent Secure Multi-Party Computation (MPC)-based methods are hindered by heavy overhead. Few recent studies explored GPUs to improve MPC-protected deep learning, yet integrating GPUs into MPC-protected DT with massive data-dependent operations remains challenging, raising question: can MPC-protected DT training and inference fully leverage GPUs for optimal performance?We present GTree, the first scheme that exploits GPU to accelerate MPC-protected secure DT training and inference. GTree is built across 3 parties who jointly perform DT training and inference with GPUs. GTree is secure against semi-honest adversaries, ensuring that no …

Lilac: Log Parsing Using Llms With Adaptive Parsing Cache, Zhihan Jiang, Jinyang Liu, Zhuangbin Chen, Yichen Li, Junjie Huang, Yintong Huo, Pinjia He, Jiazhen Gu, R. Michael Lyu

Research Collection School Of Computing and Information Systems

Log parsing transforms log messages into structured formats, serving as the prerequisite step for various log analysis tasks. Although a variety of log parsing approaches have been proposed, their performance on complicated log data remains compromised due to the use of human-crafted rules or learning-based models with limited training data. The recent emergence of powerful large language models (LLMs) demonstrates their vast pre-trained knowledge related to code and logging, making it promising to apply LLMs for log parsing. However, their lack of specialized log parsing capabilities currently hinders their parsing accuracy. Moreover, the inherent inconsistent answers, as well as the …

From A Timeline Contact Graph To Close Contact Tracing And Infection Diffusion Intervention, Yipeng Zhang, Zhifeng Bao, Yuchen Li, Baihua Zheng, Xiaoli Wang

Research Collection School Of Computing and Information Systems

This paper proposes a novel graph structure to address the problems of information spreading in a real-world, frequently updating graph, with two main contributions at hand: accurately tracing infection diffusion according to fine-grained user movements and finding vulnerable vertices under the virus immunization scenario to mitigate infection diffusion. Unlike previous work that primarily predicts the long-term epidemic trend at the census level, this study aims to intervene in the short-term at the individual level. Therefore, two downstream tasks are formulated to illustrate practicalities: Epidemic Mitigating in Public Area problem (EMA) and Epidemic Maximized Spread in Public Area problem (ESA), where …

Harnessing Collective Structure Knowledge In Data Augmentation For Graph Neural Networks, Rongrong Ma, Guansong Pang, Ling Chen

Research Collection School Of Computing and Information Systems

Graph neural networks (GNNs) have achieved state-of-the-art performance in graph representation learning. Message passing neural networks, which learn representations through recursively aggregating information from each node and its neighbors, are among the most commonly-used GNNs. However, a wealth of structural information of individual nodes and full graphs is often ignored in such process, which restricts the expressive power of GNNs. Various graph data augmentation methods that enable the message passing with richer structure knowledge have been introduced as one main way to tackle this issue, but they are often focused on individual structure features and difficult to scale up with …

Modeling And Regulating A Ride-Sourcing Market Integrated With Vehicle Rental Services, Dong Mo, Hai Wang, Zeen Cai, W. Y. Szeto, Xiqun (Michael) Chen

Research Collection School Of Computing and Information Systems

With the popularity of on-demand ride services worldwide, ride-sourcing platforms must maintain an adequate fleet size and cope with growing travel demand. Recently, platforms have attempted to provide vehicle rental services to drivers who do not own cars, then recruited them to provide on demand ride services. This helps lower the entry barrier for drivers and offers another profitable business for platforms. From the government's perspective, however, it is challenging to coordinately regulate a ride-sourcing business and vehicle rental business. This paper proposes a bi-level optimization model to investigate how the government regulates the ride-sourcing market integrated with vehicle rental …

Reinforcement Learning Based Online Request Scheduling Framework For Workload-Adaptive Edge Deep Learning Inference, Xinrui Tan, Hongjia Li, Xiaofei Xie, Lu Guo, Nirwan Ansari, Xueqing Huang, Liming Wang, Zhen Xu, Yang Liu

Research Collection School Of Computing and Information Systems

The recent advances of deep learning in various mobile and Internet-of-Things applications, coupled with the emergence of edge computing, have led to a strong trend of performing deep learning inference on the edge servers located physically close to the end devices. This trend presents the challenge of how to meet the quality-of-service requirements of inference tasks at the resource-constrained network edge, especially under variable or even bursty inference workloads. Solutions to this challenge have not yet been reported in the related literature. In the present paper, we tackle this challenge by means of workload-adaptive inference request scheduling: in different workload …

Editorial For The Special Issue Of The Metaverse, Fiona Fui-Hoon Nah, Gert-Jan De Vreede, Lakshmi Goel, Eric Lim, Shu Schiller, Chee-Wee Tan

Research Collection School Of Computing and Information Systems

The metaverse is laying the groundwork for more accessible and immersive experiences by blending the physical and virtual worlds into a unified space where people can interact, create, and connect in entirely new ways. It holds the potential to revolutionize how we work, socialize, and learn, which in turn gives rise to unprecedented opportunities for innovation. In this special issue, we present four articles that depict the current state of research in metaverse, the key themes and theoretical underpinnings within this space, as well as emerging directions for future work. This special issue delivers valuable insights for both researchers and …

Biological Reinforcement Learning Simulation For Natural Enemy -Host Behavior: Exploring Deep Learning Algorithms For Population Dynamics, Komi Mensah Agboka, Emmanuel Peter, Erion Bwambale, Bonoukpoè Mawuko Sokame

All Peer-Reviewed Publications

This study introduces a simulation of biological reinforcement learning to explore the behavior of natural enemies in the presence of host pests, aiming to analyze the population dynamics between natural enemies and insect pests within an ecological context. The simulation leverages on Q-learning, a reinforcement learning algorithm, to model the decision-making processes of both parasitoids/predators and pests, thereby assessing the impact of varying parasitism and predation rates on pest population growth. Simulation parameters, such as episode count, duration in months, steps, learning rate, and discount factor, were set arbitrarily. Environmental and reward matrices, representing climatic conditions, crop availability, and the …

Long-Term Push–Pull Cropping System Shifts Soil And Maize-Root Microbiome Diversity Paving Way To Resilient Farming System, Abdul A. Jalloh, Fathiya Mbarak Khamis, Abdullahi Ahmed Yusuf, Sevgan Subramanian, Daniel Munyao Mutyambai

All Peer-Reviewed Publications

Background: The soil biota consists of a complex assembly of microbial communities and other organisms that vary significantly across farming systems, impacting soil health and plant productivity. Despite its importance, there has been limited exploration of how different cropping systems influence soil and plant root microbiomes. In this study, we investigated soil physicochemical properties, along with soil and maize-root microbiomes, in an agroecological cereal-legume companion cropping system known as push–pull technology (PPT). This system has been used in agriculture for over two decades for insect-pest management, soil health improvement, and weed control in sub-Saharan Africa. We compared the results with …

A Mathematical Model For Mapping The Insecticide Resistance Trend In The Anopheles Gambiae Mosquito Population Under Climate Variability In Africa, Komi Mensah Agboka, Mark Wamalwa, James Mutuku Mutunga, Henri E.Z. Tonnang

All Peer-Reviewed Publications

The control of arthropod disease vectors using chemical insecticides is vital in combating malaria, however the increasing insecticide resistance (IR) poses a challenge. Furthermore, climate variability affects mosquito population dynamics and subsequently IR propagation. We present a mathematical model to decipher the relationship between IR in Anopheles gambiae populations and climate variability. By adapting the susceptible-infected-resistant (SIR) framework and integrating temperature and rainfall data, our model examines the connection between mosquito dynamics, IR, and climate. Model validation using field data achieved 92% accuracy, and the sensitivity of model parameters on the transmission potential of IR was elucidated (e.g. μPRCC = …

Introducing The Second-Order Features Adjoint Sensitivity Analysis Methodology For Neural Ordinary Differential Equations—Ii: Illustrative Application To Heat And Energy Transfer In The Nordheim–Fuchs Phenomenological Model For Reactor Safety, Dan Gabriel Cacuci

Faculty Publications

This work presents an illustrative application of the newly developed “Second-Order Features Adjoint Sensitivity Analysis Methodology for Neural Ordinary Differential Equations (2nd-FASAM-NODE)” methodology to determine most efficiently the exact expressions of the first- and second-order sensitivities of NODE decoder responses to the neural net’s underlying parameters (weights and initial conditions). The application of the 2nd-FASAM-NODE methodology will be illustrated using the Nordheim–Fuchs phenomenological model for reactor safety, which describes a short-time self-limiting power transient in a nuclear reactor system having a negative temperature coefficient in which a large amount of reactivity is suddenly inserted. The representative model responses that will …

Towards Verified Vision-Based Neural Network Controllers For Autonomous Lane-Following, Xinhang Ma

McKelvey School of Engineering Graduate Student Theses & Dissertations

Vision-based neural network controllers have shown promising results in autonomous lane-following tasks, but verifying their safety properties remains a significant challenge due to the high dimensionality of image inputs. This thesis designs an approach to enable formal verification of vision-based lane-following controllers by first developing an end-to-end autonomous system combining deep learning-based lane detection with reinforcement learning control. To enable formal verification, we introduce a generator-based framework that bridges the gap between high-dimensional image space and low-dimensional vehicle states, allowing us to leverage existing verification tools while maintaining the vision-based nature of the controller.

We further enhance our verification framework …

Evaluation Of Industrial Hemp Cultivar And Biochar Rate To Remediate Heavy-Metal-Contaminated Soil From The Tar Creek Superfund Site, Usa, Dietrich V. Thurston, Kristofor R. Brye, David M. Miller, Philip A. Moore Jr., Donald M. Johnson, Mike Richardson

Crop, Soil and Environmental Sciences Faculty Publications and Presentations

Soil contamination by cadmium (Cd), lead (Pb), and zinc (Zn) at the Tar Creek superfund site in northeast Oklahoma, United States, remains a threat to the environment and local ecosystem. Phytoremediation with industrial hemp (Cannabis sativa L.) and the use of biochar (BC) have been independently shown to be effective methods to remediate heavy-metal-contaminated soils. The objective of this greenhouse study was to evaluate the effects of industrial hemp cultivar (‘Carmagnola’ and ‘Jinma’), biochar rate (0, 2, 5, and 10% by volume), soil contamination level (low, medium, and high), and their interactions on above- (AG) and belowground dry matter …

Rice Response To Struvite And Other Phosphorus Fertilizers In A Phosphorus-Deficient Soil Under Simulated Furrow-Irrigation, Jonathan B. Brye, Diego Della Lunga, Kristofor R. Brye

Crop, Soil and Environmental Sciences Faculty Publications and Presentations

Wastewater-recovered phosphorus (P), in the form of the mineral struvite (MgNH₄PO₄⋅6H₂O), may provide a sustainable alternative to decreasing rock-phosphate reserves. Struvite can be generated via precipitation methods, potentially reducing the amount of P runoff to aquatic ecosystems. The objective of this greenhouse tub study was to evaluate the effects of chemically- and electrochemically precipitated struvite (CPST and ECST, respectively) on above- and belowground plant response in a hybrid rice (Oryza sativa) cultivar grown using furrow-irrigation compared to other common fertilizer-P sources [i.e., triple super phosphate (TSP) and diammonium phosphate (DAP)]. Rice was …

Benefits Of Teaching Pre-Literacy In Waldorf Education In Early Childhood, April Guerrero

Capstone Projects and Master's Theses

This senior capstone research project examines the benefits of teaching pre-literacy in Waldorf education in early childhood. In Waldorf Education, literacy development incorporates differentiated instructions that fosters cognitive and social emotional learning of their students. Through the use of literature review and several teachers in various grades of Waldorf schools, the result findings revealed that pedagogical practices around literacy instructions promote critical thinking skills, nurtures children’s creative expression, and imagination. Literacy curriculum in Waldorf schools allows students to create tangible evidence of self-expressions and communication skills. Given its emphasis on holistic curriculum, it allows teachers to engage with their diverse …

Survival Of The Smartest? The Evolutionary Ecology Of Cognition In Anolis Lizards, Mahaut V. Sorlin

LSU New Orleans Theses and Dissertations

Cognitive processes such as learning, memory, and decision-making are integral to an organism’s fitness, allowing to integrate cues from its environment and adjust its behavior accordingly. Historically, cognitive abilities were thought to have evolved according to a Scala Naturae design—an idea that has since been disproven—which suggested that complex cognitive abilities were exclusive to “higher” taxa. This perspective has created significant phylogenetic gaps in our understanding of cognitive evolution. In this dissertation I aimed to address this issue by investigating the evolution of cognition in reptiles, focusing on the green (Anolis carolinensis) and the brown anole (Anolis …

Deep Learning Approach For Accurate Segmentation Of Oil Spills In Marine Systems, Mohamed Elsheref

LSU New Orleans Theses and Dissertations

Oil spills present critical environmental hazards, threatening marine ecosystems and necessitating fast, accurate detection for effective mitigation. Synthetic Aperture Radar (SAR) imagery has been instrumental in detecting oil spills, but manual interpretation is often inefficient and prone to errors. This study addresses the limitations of manual methods by proposing a deep learning approach for automated oil spill detection and segmentation.

Utilizing a novel transfer learning-based semantic segmentation model, this research focuses on detecting oil slicks on the sea surface with higher accuracy and efficiency. The model leverages pre-trained networks and incorporates U-Net variants, including UNet++ and MultiResUNet, to optimize spatial …

New Constraints On The Stratigraphic Architecture And Evolution Of Mississippi River Delta Lobe Activity: Barataria Basin, Southeastern La, Wilke Coleman

LSU New Orleans Theses and Dissertations

Barataria Basin is a shallow water, interdistributary estuary that has evolved in response to dynamic depositional regimes governed by distributary avulsion and reworking of sediments by coastal processes. In the Mississippi River delta plain, the migratory nature of the River has produced an evolving landscape constructed through episodes of regressive and transgressive sedimentation. These processes produce unique depositional signatures in the stratigraphic record, however the transgressive component of the delta cycle often results in obliteration of the regressive phase. This study uses a modern suite of geophysical and sediment core data to construct a revised geologic framework in Barataria Basin, …

Benefits Of After School Programs On The Academic Success On Lower Elementary School Students, Jessica Rodriguez Rodriguez

Capstone Projects and Master's Theses

After School programs offer significant benefits to students. They support students by offering tutoring, homework assistance, enrichment activities that reinforce classroom learning, and helping young students develop essential skills in reading, math, and critical thinking. The purpose of my capstone project is to examine the benefits of afterschool programs on the academic success of lower elementary school students. Through literature review, interviews with teachers, a coordinator, an academic coordinator, an administrator, and anonymous student surveys, the result findings indicated that afterschool programs are important and have benefited students in meeting their needs to foster their success. It also highlights the …

The Impact Of Single Parent Households On Middle School Students, Erik Puga

Capstone Projects and Master's Theses

This research explores the influence of single-parent households on the academic achievement of middle school students in Salinas, CA, with a particular focus on East Salinas, an area marked by economic challenges. Grounded in my personal experience growing up in a single-parent household in Salinas and shaped by my journey through the Alisal district pipeline, this study seeks to uncover the specific barriers and strengths that middle school students from single-parent families encounter. By examining socioeconomic pressures, parental involvement, and emotional well-being, I aim to identify how family structure affects students’ educational trajectories within the community. This research strives to …

Draft Final 2022 Insufficiently Reclaimed Sites Sampling Bres No. 37 – Josephine Shaft Site Evaluation Summary Report, Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Jürgen Habermas Revisited Via Tim Cook's Wikipedia Biography: A Hermeneutic Approach To Critical Information Systems Research, Reilly Smethurst, Amber G. Young, Arial D. Wigdor

Information Systems Faculty Publications and Presentations

Critical Information Systems (IS) research is sometimes appreciated for the shades of gray it adds to sunny portraits of technology's emancipatory potential. In this article, we revisit a theory about Wikipedia’s putative freedom from the authority of corporate media's editors and authors. We present the curious example of Tim Cook's Wikipedia biography and its history of crowd-sourced editorial decisions, published on Wikipedia's talk pages. We use a hermeneutic method to subject the theory about Wikipedia's “rational discourse” and “emancipatory potential” to a soft, empirical test. When we examined Cook's Wikipedia biography and its editorial decisions, what we found pertained to …

United We Stand, Divided We Fall: An Autogenic Perspective On Empowering Cybersecurity In Organizations, Alexandra Durcikova, Shayla M. Miranda, Matthew L. Jensen, Ryan T. Wright

Information Systems Faculty Publications and Presentations

Cybersecurity groups navigate complex, challenging environments in their mission to protect their organizations. They experience uncertainty from adaptive threats from external attackers and unpredictable stakeholders. Under such volatility, business groups operate best when they are psychologically empowered. Recognizing the potential for empowerment to reduce organizational risk, we sought to learn how cybersecurity groups come to be (dis)empowered and how this (dis)empowerment is sustained. Instead of the conventional view of the empowerment process as designed, we advance an emergent view of the empowerment process. We abductively surface this process from our case analyses of 15 U.S. organizations. We offer three insights: …

An Exploration Of Machine Learning Security, Carson Kendall Grandi Koball

Masters Theses & Doctoral Dissertations

Innovations in the fields of computer science and mathematics have enabled machines to learn incredibly complicated patterns and abstractions without explicit tutoring. Unfortunately, threats have been developed targeting machine learning systems that may affect large groups of individuals including model producers and maintainers, model users, and individuals who may be implicitly or explicitly represented by the information used by the model. Consequently, it is crucial to understand possible attacks that may be employed on machine learning models at the algorithmic level for better mitigation strategies. This research seeks to work towards a better understanding of vulnerabilities that exist in the …

Experimental Investigations Of Wind Shear From Passing A Vehicle, Hamid Rahai, Assma Begum, Jeremy Bonifacio, Ryan Moffit

Mineta Transportation Institute

Wind energy can be harnessed for various commercial and transportation-related applications. This study assessed experimentally the potential of capturing wind energy from the passage of vehicles for electric power generation. Both wind tunnel experiments and field tests were performed. The wind tunnel experiments were performed in an open-circuit low-speed wind tunnel at a free-stream mean velocity of 23 m/s. Five PVC pipes placed adjacent to the wind-blowing domain were used to simulate the columns under a freeway overpass. A scaled Ahmad body (simplified car body model) was used as the vehicle. The spanwise distance between the Ahmad body and the …

Latent Characterization Of The Complete Batse Gamma-Ray Bursts Catalogue Using Gaussian Mixture Of Factor Analysers And Model-Estimated Overlap-Based Syncytial Clustering, Fan Dai, Ranjan Maitra

Michigan Tech Publications

Characterizing and distinguishing gamma-ray bursts (GRBs) has interested astronomers for many decades. While some authors have found two or three groups of GRBs by analysing only a few parameters, recent work identified five ellipsoidally shaped groups upon considering nine parameters T50, T90, F1, F2, F3, F4, P64, P256, P1024. Yet others suggest subclasses within the two or three groups found earlier. Using a mixture model of Gaussian factor analysers, we analysed 1150 GRBs, that had nine parameters observed, from the current Burst and Transient Source Experiment (BATSE) catalogue, and again established five ellipsoidal-shaped groups to describe the GRBs. These five …

Potential Effect Of Produced Water Discharge On Surface Water: Lower Atascosa River Study, Alejandro Mendietta

Water Resources Science and Technology Theses and Graduate Research Reports (Archived)

This study investigates the potential impact of an approved produced water discharge permit in the Atascosa River. Water samples were collected from a test site on the Atascosa River and analyzed for key water quality parameters such as chloride, total dissolved solids, sodium, calcium, strontium and other ions. These results were compared to historical data from the local river authority to assess any significant changes in water quality following the permit's approval in April 2024. Statistical analyses, including averages and t-tests, were conducted to determine whether the current ion concentrations differed significantly from historical levels. While an increase in concentrations …

Detection Of Per- And Polyfluoroalkyl Substances In Public Water Supply: San Antonio Case Study, David Arambula

Water Resources Science and Technology Theses and Graduate Research Reports (Archived)

This research investigates the detection and influence of per- and polyfluoroalkyl substances (PFAS) in the San Antonio water supply system, focusing on two contaminated water entry points sourced from the Edwards Aquifer. Sampling and statistical analyses compare urbanization, geologic features, and groundwater quality between contaminated and noncontaminated sites. Key findings include statistically significant differences in fault lengths, impermeable surfaces, and urban development. Although direct correlations between PFAS contamination and groundwater quality parameters like nitrate and conductivity remain inconclusive due to limited data, the study indicates urbanization's potential role in exacerbating PFAS infiltration through sensitive geological features. Insights from this research …

Patterns Of Interactions In Human-Machine Teams, Kazuhiko Momose

Theses and Dissertations

Increasingly capable machines, including Artificial Intelligence (AI) agents are playing a more important role in a wide range of applications, including human daily activities and safety-critical systems. They can benefit even more when humans and such machines agents work together as a team by leveraging each other's strengths and complementing each other to enhance overall performance. To design high-performing teams, it is critical to analyze the team dynamics and understand how humans and machines interact with each other. Collaboration, Coordination, and Cooperation (3Cs) are terms typically used to describe the behavior of teams. However, these terms tend to be used …

Elucidating The Significant Roles Of Root Exudates In Organic Pollutant Biotransformation Within The Rhizosphere, Michael O. Eze, Chinedu F. Amuji

Chemistry Faculty Research & Creative Works

Biotransformation of organic pollutants is crucial for the dissipation of environmental pollutants. While the roles of microorganisms have been extensively studied, the significant contribution of various root exudates are still not very well understood. Through plant growth experiment, coupled with gas and liquid chromatography-mass spectrometry methods, this study examined the effect of the presence of M. sativa on microbial-associated biochemical transformation of petroleum hydrocarbons. The results of this study revealed that the concentration of exudates within the soil matrix is a function of proximity to root surfaces. Similarly, biodegradation was found to correlate with distance from roots, ranging from ≥ …