Physical Sciences and Mathematics Commons^™

A Technical Perspective On Integrating Artificial Intelligence To Solid-State Welding, Sambath Yaknesh, Natarajan Rajamurugu, Prakash K. Babu, Saravanakumar Subramaniyan, Sher A. Khan, C. Ahamed Saleel, Mohammad Nur-E-Alam, Manzoore E. M. Soudagar

Research outputs 2022 to 2026

The implementation of artificial intelligence (AI) techniques in industrial applications, especially solid-state welding (SSW), has transformed modeling, optimization, forecasting, and controlling sophisticated systems. SSW is a better method for joining due to the least melting of material thus maintaining Nugget region integrity. This study investigates thoroughly how AI-based predictions have impacted SSW by looking at methods like Artificial Neural Networks (ANN), Fuzzy Logic (FL), Machine Learning (ML), Meta-Heuristic Algorithms, and Hybrid Methods (HM) as applied to Friction Stir Welding (FSW), Ultrasonic Welding (UW), and Diffusion Bonding (DB). Studies on Diffusion Bonding reveal that ANN and Generic Algorithms can predict outcomes …

Expanding Australia's Defence Capabilities For Technological Asymmetric Advantage In Information, Cyber And Space In The Context Of Accelerating Regional Military Modernisation: A Systemic Design Approach, Pi-Shen Seet, Anton Klarin, Janice Jones, Michael N. Johnstone, Violetta Wilk, Stephanie Meek, Summer O'Brien

Research outputs 2022 to 2026

Introduction. The aim of the project was to conduct a systemic design study to evaluate Australia'sopportunities and barriers for achieving a technological advantage in light of regional military technological advancement. It focussed on the three domains of (1) cybersecurity technology, (2) information technology, and (3) space technology.

Research process. Employing a systemic design approach, the study first leveraged scientometric analysis, utilising informetric mapping software (VOSviewer) to evaluate emerging trends and their implications on defence capabilities. This approach facilitated a broader understanding of the interdisciplinary nature of defence technologies, identifying key areas for further exploration. The subsequent survey study, engaging 828 …

Unifying Context With Labeled Property Graph: A Pipeline-Based System For Comprehensive Text Representation In Nlp, Ali Hur, Naeem Janjua, Mohiuddin Ahmed

Research outputs 2022 to 2026

Extracting valuable insights from vast amounts of unstructured digital text presents significant challenges across diverse domains. This research addresses this challenge by proposing a novel pipeline-based system that generates domain-agnostic and task-agnostic text representations. The proposed approach leverages labeled property graphs (LPG) to encode contextual information, facilitating the integration of diverse linguistic elements into a unified representation. The proposed system enables efficient graph-based querying and manipulation by addressing the crucial aspect of comprehensive context modeling and fine-grained semantics. The effectiveness of the proposed system is demonstrated through the implementation of NLP components that operate on LPG-based representations. Additionally, the proposed …

Mhair: A Dataset Of Audio-Image Representations For Multimodal Human Actions, Muhammad Bilal Shaikh, Douglas Chai, Syed M. S. Islam, Naveed Akhtar

Research outputs 2022 to 2026

Audio-image representations for a multimodal human action (MHAiR) dataset contains six different image representations of the audio signals that capture the temporal dynamics of the actions in a very compact and informative way. The dataset was extracted from the audio recordings which were captured from an existing video dataset, i.e., UCF101. Each data sample captured a duration of approximately 10 s long, and the overall dataset was split into 4893 training samples and 1944 testing samples. The resulting feature sequences were then converted into images, which can be used for human action recognition and other related tasks. These images can …

Multimodal Fusion For Audio-Image And Video Action Recognition, Muhammad B. Shaikh, Douglas Chai, Syed M. S. Islam, Naveed Akhtar

Research outputs 2022 to 2026

Multimodal Human Action Recognition (MHAR) is an important research topic in computer vision and event recognition fields. In this work, we address the problem of MHAR by developing a novel audio-image and video fusion-based deep learning framework that we call Multimodal Audio-Image and Video Action Recognizer (MAiVAR). We extract temporal information using image representations of audio signals and spatial information from video modality with the help of Convolutional Neutral Networks (CNN)-based feature extractors and fuse these features to recognize respective action classes. We apply a high-level weights assignment algorithm for improving audio-visual interaction and convergence. This proposed fusion-based framework utilizes …

Effects Of Voice Pitch On Social Perceptions Vary With Relational Mobility And Homicide Rate, Toe Aung, Et. Al

Research Collection School of Social Sciences

Fundamental frequency (fo) is the most perceptually salient vocal acoustic parameter, yet little is known about how its perceptual influence varies across societies. We examined how fo affects key social perceptions and how socioecological variables modulate these effects in 2,647 adult listeners sampled from 44 locations across 22 nations. Low male fo increased men’s perceptions of formidability and prestige, especially in societies with higher homicide rates and greater relational mobility in which male intrasexual competition may be more intense and rapid identification of highstatus competitors may be exigent. High female fo increased women’s perceptions of flirtatiousness where relational mobility was …

Modeling Earthquake Catalog (1985-2022) In Northern Egypt Using Space-Time Epidemic-Type Aftershock Sequences (Etas), Mariam Ramadan, Amir Ismail, Amin E. Khalil, Hesham Abdelhafiez, Nouran S. Salama

Trends in advanced sciences and technology

Earthquakes have the largest damaging effects among natural disasters on a global scale. Efforts for reducing their effects have taken place for a long time. The prediction of earthquakes was the main target, however the studies conducted were not successful. As a replacement, seismic hazard assessments were adopted to predict the levels of ground motion for the possible future large earthquakes. This approach is probabilistic in nature that rely on the quality of earthquake catalog. The probabilistic model adopted is built on the assumption that the events in the earthquake catalog are random Poisson distribution, assuming that events are independent …

Cyberbullying Text Identification: A Deep Learning And Transformer-Based Language Modeling Approach, Khalid Saifullah, Muhammad Ibrahim Khan, Suhaima Jamal, Iqbal H. Sarker

Research outputs 2022 to 2026

In the contemporary digital age, social media platforms like Facebook, Twitter, and YouTube serve as vital channels for individuals to express ideas and connect with others. Despite fostering increased connectivity, these platforms have inadvertently given rise to negative behaviors, particularly cyberbullying. While extensive research has been conducted on high-resource languages such as English, there is a notable scarcity of resources for low-resource languages like Bengali, Arabic, Tamil, etc., particularly in terms of language modeling. This study addresses this gap by developing a cyberbullying text identification system called BullyFilterNeT tailored for social media texts, considering Bengali as a test case. The …

From Grain To Malt: Tracking Changes Of Ultra-Low-Gluten Barley Storage Proteins After Malting, Mahya Bahmani, Angéla Juhász, Utpal Bos, Mitchell G. Nye-Wood, Malcolm Blundell, Crispin A. Howitt, Michelle L. Colgrave

Research outputs 2022 to 2026

Barley (Hordeum vulgare L.) is a major cereal crop produced globally. Hordeins, the major storage proteins in barley, can trigger immune responses leading to celiac disease or symptoms associated with food allergy. Here, proteomics approaches were employed to investigate the proteome level changes of grain and malt from the malting barley cultivar, Sloop, and single-, double- and triple hordein-reduced lines. The triple hordein-reduced line is an ultra-low gluten barley cultivar, Kebari®. Using discovery proteomics, 2,688 and 3,034 proteins in the barley and malt samples were detected respectively. Through the application of targeted proteomics, a significant reduction in the quantity …

Economic Material For Large-Scale H2 Storage And H2-Co2 Separation, Hussein R. Abid, Alireza Keshavarz, Header Jaffer, Basim K. Nile, Stefan Iglauer

Research outputs 2022 to 2026

Hydrogen is a clean fuel that can potentially completely decarbonize the energy supply chain and mitigate global warming. Hydrogen – a highly volatile gas – however, needs to be separated from CO2 during H2 production, and also from cushion gas in H2 geo-storage projects; in addition, large-scale H2 storage is a key obstacle. We thus tested and chemically upgraded common sub-bituminous coal as a material for H2-CO2 separation and H2 storage. The coal adsorbed significant amounts of H2 and CO2 and demonstrated an excellent H2-CO2 separation efficiency if chemically modified. The work presented here thus provides fundamental data required for …

Analysis Of Element Yield, Bacterial Community Structure And The Impact Of Carbon Sources For Bioleaching Rare Earth Elements From High Grade Monazite, Melissa K. Corbett, April Gifford, Nick Fimognari, Elizabeth L. J. Watkin

Research outputs 2022 to 2026

Rare earth element (REE) recovery from waste streams, mine tailings or recyclable components using bioleaching is gaining traction due to the shortage and security of REE supply as well as the environmental problems that occur from processing and refining. Four heterotrophic microbial species with known phosphate solubilizing capabilities were evaluated for their ability to leach REE from a high-grade monazite when provided with either galactose, fructose or maltose. Supplying fructose resulted in the greatest amount of REE leached from the ore due to the largest amount of organic acid produced. Gluconic acid was the dominant organic acid identified produced by …

Malware Detection With Artificial Intelligence: A Systematic Literature Review, Matthew G. Gaber, Mohiuddin Ahmed, Helge Janicke

Research outputs 2022 to 2026

In this survey, we review the key developments in the field of malware detection using AI and analyze core challenges. We systematically survey state-of-the-art methods across five critical aspects of building an accurate and robust AI-powered malware-detection model: malware sophistication, analysis techniques, malware repositories, feature selection, and machine learning vs. deep learning. The effectiveness of an AI model is dependent on the quality of the features it is trained with. In turn, the quality and authenticity of these features is dependent on the quality of the dataset and the suitability of the analysis tool. Static analysis is fast but is …

Agricultural Groundcover Update December 2023, Justin Laycock

Natural resources published reports

Summary

• About 96% of the grainbelt had adequate vegetative groundcover (more than 50%) to prevent wind erosion in December 2023.
• In the northern half of the grainbelt, a larger-than-average area has 51–60% groundcover, which is expected to decrease to below 50% over the summer.
• Just under 4% of the grainbelt (553,000 ha) had less than 50% groundcover, which is inadequate to prevent wind erosion. West Midlands Ag Soil Zone had the highest risk of wind erosion and 11.4% of this farmland had inadequate groundcover.
• Less than 0.5% of the grainbelt had a high to very high risk of wind erosion …

In Pursuit Of Consumption-Based Forecasting, Charles Chase, Kenneth B. Kahn

Marketing Faculty Publications

[Introduction] Today's most mature, most sophisticated, best-in-class forecasting is what we call consumption-based forecasting (CBF). In contrast, the least sophisticated companies typically do not forecast at all, but rather set financial targets based on management expectations. Companies beginning to use statistical forecasting techniques usually take a supply-centric orientation, relying on time series techniques applied to shipment and/or order history. The next stage of progression is to incorporate promotions data, economic data, and market data alongside supply-centric data so that regression and other advanced analytics can be used. Companies pursing CBF utilize even more advanced capabilities to capture, examine, and understand …

Constrained Multiview Representation For Self-Supervised Contrastive Learning, Siyuan Dai, Kai Ye, Kun Zhao, Ge Cui, Haoteng Tang, Liang Zhan

Computer Science Faculty Publications and Presentations

Representation learning constitutes a pivotal cornerstone in contemporary deep learning paradigms, offering a conduit to elucidate distinctive features within the latent space and interpret the deep models. Nevertheless, the inherent complexity of anatomical patterns and the random nature of lesion distribution in medical image segmentation pose significant challenges to the disentanglement of representations and the understanding of salient features. Methods guided by the maximization of mutual information, particularly within the framework of contrastive learning, have demonstrated remarkable success and superiority in decoupling densely intertwined representations. However, the effectiveness of contrastive learning highly depends on the quality of the positive and …

A Simple Proof That Ricochet Robots Is Pspace-Complete, Jose Balanza-Martinez, Angel A. Cantu, Robert Schweller, Tim Wylie

Computer Science Faculty Publications and Presentations

In this paper, we seek to provide a simpler proof that the relocation problem in Ricochet Robots (Lunar Lockout with fixed geometry) is PSPACE-complete via a reduction from Finite Function Generation (FFG). Although this result was originally proven in 2003, we give a simpler reduction by utilizing the FFG problem, and put the result in context with recent publications showing that relocation is also PSPACE-complete in related models.

Efficient High-Resolution Time Series Classification Via Attention Kronecker Decomposition, Aosong Feng, Jialin Chen, Juan Garza, Brooklyn Berry, Francisco Salazar, Yifeng Gao, Rex Ying, Leandros Tassiulas

Computer Science Faculty Publications and Presentations

The high-resolution time series classification problem is essential due to the increasing availability of detailed temporal data in various domains. To tackle this challenge effectively, it is imperative that the state-of-theart attention model is scalable to accommodate the growing sequence lengths typically encountered in highresolution time series data, while also demonstrating robustness in handling the inherent noise prevalent in such datasets. To address this, we propose to hierarchically encode the long time series into multiple levels based on the interaction ranges. By capturing relationships at different levels, we can build more robust, expressive, and efficient models that are capable of …

Growing Up Sustainable? Politics Of Race And Youth In Urbanplan, Copenhagen, Max Ritts, Rebecca Rutt

Geography

This paper considers how racialized youth in Denmark negotiate sustainability amid contexts marked by intersecting forms of economic restructuring, progressive neoliberalism, white ethno-nationalism, and green urban planning. Urbanplan is a low-income, notoriously “troubled” Copenhagen neighborhood where we conducted fieldwork for 7 months (2019-2020) with fifteen male youth, aged 17-21. Using ethnography, policy reviews, and interviews with city social workers, we explore how intimate experiences of nature, group-identity, and place attachment here relate to and depart from the structural forces actively reshaping the neighborhood. Our analysis combines Cindi Katz's intersectional political economy approach with recent work on green gentrification, Critical Utopian …

Reducing Short-Chain Pfas Levels In California Water Supplies, Manu Prabandham

Pomona Senior Theses

This thesis proposes twelve specific policies based on precedents set by prior regulation of persistent organic pollutants (such as PCBs), the costs and benefits of short-chain PFAS, technologies available to remove and destroy short-chain PFAS, and the roles and limitations of California’s regulatory institutions. The twelve policies are chosen to be politically and financially feasible, effective at removing short-chain PFAS from water supplies, and equitable towards lower-income and minority Californians, who suffer the most from the consequences of PFAS and other environmental pollutants. The new definitions, education campaigns, studies, taxes, bans, standards, testing, and filtration systems proposed are intended to …

Mechanisms Of Dendritic Shorting In Lithium Metal Batteries With Li7la3zr2o12 Solid Electrolytes, Lukas Karapin-Springorum

Pomona Senior Theses

Energy storage will play a crucial role in efforts to mitigate the effects of climate change caused by greenhouse gas emissions from human activity. Lithium metal batteries using solid electrolytes like Li₇La₃Zr₂O₁₂ have higher energy density than lithium-ion batteries, which may enable a more rapid and complete electrification of transportation. However, lithium metal batteries suffer from undesirable short-circuiting when metallic lithium deposits connect the two electrodes. It has been debated whether these lithium dendrites generally grow directionally from the anode or are generated by the reduction of lithium ions inside the solid electrolyte, …

Self Pre-Training With Topology- And Spatiality-Aware Masked Autoencoders For 3d Medical Image Segmentation, Pengfei Gu, Yejia Zhang, Huimin Li, Chaoli Wang, Danny Z. Chen

Computer Science Faculty Publications and Presentations

Masked Autoencoders (MAEs) have been shown to be effective in pre-training Vision Transformers (ViTs) for natural and medical image analysis problems. By reconstructing missing pixel/voxel information in visible patches, a ViT encoder can aggregate contextual information for downstream tasks. But, existing MAE pre-training methods, which were specifically developed with the ViT architecture, lack the ability to capture geometric shape and spatial information, which is critical for medical image segmentation tasks. In this paper, we propose a novel extension of known MAEs for self pre-training (i.e., models pre-trained on the same target dataset) for 3D medical image segmentation. (1) We propose …

Complete Solution Of The Lady In The Lake Scenario, Alexander Von Moll, Meir Pachter

Faculty Publications

In the Lady in the Lake scenario, a mobile agent, L, is pitted against an agent, M, who is constrained to move along the perimeter of a circle. L is assumed to begin inside the circle and wishes to escape to the perimeter with some finite angular separation from M at the perimeter. This scenario has, in the past, been formulated as a zero-sum differential game wherein L seeks to maximize terminal separation and M seeks to minimize it. Its solution is well-known. However, there is a large portion of the state space for which the canonical solution does not …

Garbage In ≠ Garbage Out: Exploring Gan Resilience To Image Training Set Degradations, Nicholas Crino, Bruce A. Cox, Nathan B. Gaw

Faculty Publications

Generative Adversarial Networks (GANs) have received immense attention in recent years due to their ability to capture complex, high-dimensional data distributions without the need for extensive labeling. Since their conception in 2014, a wide array of GAN variants have been proposed featuring alternative architectures, optimizers, and loss functions with the goal of improving performance and training stability. This manuscript focuses on quantifying the resilience of a GAN architecture to specific modes of image degradation. We conduct systematic experimentation to empirically determine the effects of 10 fundamental image degradation modes, applied to the training image dataset, on the Fréchet inception distance …

Enhancing Decision-Making In Higher Education: Exploring The Integration Of Chatgpt And Data Visualization Tools In Data Analysis, Tristan Jiang, Elina Liu, Tasawar Baig, Qingrong Li

University Administration Publications

This chapter explores the potential of integrating conversational AI tools such as ChatGPT with data visualization (DV) tools such as Power BI in higher education settings. A brief history of chatbots is summarized and challenges and opportunities in higher education are outlined. The highlights include AI's prospects for enhancing data-informed decision-making while needing safeguards to mitigate risks. Through a pioneering exercise, we integrated ChatGPT's conversational capabilities with Power BI's interface via API and tested functionality. Suggestions for good practice and implications for higher education are discussed.

Using Phenology To Unravel Differential Soil Water Use And Productivity In A Semiarid Savanna, Blake Steiner, Russell L. Scott, Jia Hu, Natasha Mcbean, Andrew Richardson, David J. P. Moore

University Administration Publications

Savannas are water-limited ecosystems characterized by two dominant plant types: trees and an understory primarily made up grass. Different phenology and root structures of these plant types complicate how savanna primary productivity responds to changes in water availability. We tested the hypothesis that productivity in savannas is controlled by the temporal and vertical distribution of soil water content (SWC) and differences in growing season length of understory and tree plant functional types. To quantify the relationship between tree, understory, and savanna-wide phenology and productivity, we used PhenoCam and satellite observations surrounding an eddy covariance tower at a semiarid savanna site …

Trace And Rare Earth Elements Analysis Of Oligocene And Miocene Diamictites In The Cape Roberts Project, Ross Sea, Antarctica, Celina Flores Garza

Theses, Dissertations and Culminating Projects

The West Antarctic Ice Sheet is a major contributor to global sea level rise, yet its origin and dynamics are poorly known. The geochemistry of 35 diamictite samples from the CRP-1 and CPR-2A cores recovered by the Cape Roberts Drilling Project in the Ross Sea, Antarctica is evaluated to understand glacial sedimentation and flow paths during the Oligocene and Miocene, a period of warmer than present climate in the past. The major hypothesis to be tested is if the early Miocene ice sheet advance was the first major West Antarctic ice advance in the Ross Sea. The provenance of older …