Physical Sciences and Mathematics Commons^™

Faire: Repairing Fairness Of Neural Networks Via Neuron Condition Synthesis, Tianlin Li, Xiaofei Xie, Jian Wang, Qing Guo, Aishan Liu, Lei Ma, Yang Liu

Research Collection School Of Computing and Information Systems

Deep Neural Networks (DNNs) have achieved tremendous success in many applications, while it has been demonstrated that DNNs can exhibit some undesirable behaviors on concerns such as robustness, privacy, and other trustworthiness issues. Among them, fairness (i.e., non-discrimination) is one important property, especially when they are applied to some sensitive applications (e.g., finance and employment). However, DNNs easily learn spurious correlations between protected attributes (e.g., age, gender, race) and the classification task and develop discriminatory behaviors if the training data is imbalanced. Such discriminatory decisions in sensitive applications would introduce severe social impacts. To expose potential discrimination problems in DNNs …

Pro-Cap: Leveraging A Frozen Vision-Language Model For Hateful Meme Detection, Rui Cao, Ming Shan Hee, Adriel Kuek, Wen Haw Chong, Roy Ka-Wei Lee, Jing Jiang

Research Collection School Of Computing and Information Systems

Hateful meme detection is a challenging multimodal task that requires comprehension of both vision and language, as well as cross-modal interactions. Recent studies have tried to fine-tune pre-trained vision-language models (PVLMs) for this task. However, with increasing model sizes, it becomes important to leverage powerful PVLMs more efficiently, rather than simply fine-tuning them. Recently, researchers have attempted to convert meme images into textual captions and prompt language models for predictions. This approach has shown good performance but suffers from non-informative image captions. Considering the two factors mentioned above, we propose a probing-based captioning approach to leverage PVLMs in a zero-shot …

On The Sustainability Of Deep Learning Projects: Maintainers' Perspective, Junxiao Han, Jiakun Liu, David Lo, Chen Zhi, Yishan Chen, Shuiguang Deng

Research Collection School Of Computing and Information Systems

Deep learning (DL) techniques have grown in leaps and bounds in both academia and industry over the past few years. Despite the growth of DL projects, there has been little study on how DL projects evolve, whether maintainers in this domain encounter a dramatic increase in workload and whether or not existing maintainers can guarantee the sustained development of projects. To address this gap, we perform an empirical study to investigate the sustainability of DL projects, understand maintainers' workloads and workloads growth in DL projects, and compare them with traditional open-source software (OSS) projects. In this regard, we first investigate …

Revisiting Disentanglement And Fusion On Modality And Context In Conversational Multimodal Emotion Recognition, Bobo Li, Hao Fei, Lizi Liao, Yu Zhao, Chong Teng, Tat-Seng Chua, Donghong Ji, Fei Li

Research Collection School Of Computing and Information Systems

It has been a hot research topic to enable machines to understand human emotions in multimodal contexts under dialogue scenarios, which is tasked with multimodal emotion analysis in conversation (MM-ERC). MM-ERC has received consistent attention in recent years, where a diverse range of methods has been proposed for securing better task performance. Most existing works treat MM-ERC as a standard multimodal classification problem and perform multimodal feature disentanglement and fusion for maximizing feature utility. Yet after revisiting the characteristic of MM-ERC, we argue that both the feature multimodality and conversational contextualization should be properly modeled simultaneously during the feature disentanglement …

Heterogeneous Graph Neural Network With Multi-View Representation Learning, Zezhi Shao, Yongjun Xu, Wei Wei, Fei Wang, Zhao Zhang, Feida Zhu

Research Collection School Of Computing and Information Systems

In recent years, graph neural networks (GNNs)-based methods have been widely adopted for heterogeneous graph (HG) embedding, due to their power in effectively encoding rich information from a HG into the low-dimensional node embeddings. However, previous works usually easily fail to fully leverage the inherent heterogeneity and rich semantics contained in the complex local structures of HGs. On the one hand, most of the existing methods either inadequately model the local structure under specific semantics, or neglect the heterogeneity when aggregating information from the local structure. On the other hand, representations from multiple semantics are not comprehensively integrated to obtain …

Ppdf: A Privacy-Preserving Cloud-Based Data Distribution System With Filtering, Yudi Zhang, Willy Susilo, Fuchun Guo, Guomin Yang

Research Collection School Of Computing and Information Systems

Cloud computing has emerged as a popular choice for distributing data among both individuals and companies. Ciphertext-policy attribute-based encryption (CP-ABE) has been extensively used to provide data security and enable fine-grained access control. With this encryption technique, only users whose attributes satisfy the access policy can access the plaintext. In order to mitigate the computational overhead on users, particularly on lightweight devices, partial decryption has been introduced, where the cloud assists in performing the decryption computations without revealing sensitive information. However, in this process, the cloud obtains the user's attributes, thus infringing on the user's privacy. To address this issue, …

Demo Abstract: Vgglass - Demonstrating Visual Grounding And Localization Synergy With A Lidar-Enabled Smart-Glass, Darshana Rathnayake, Dulanga Weerakoon, Meeralakshmi Radhakrishnan, Vigneshwaran Subbaraju, Inseok Hwang, Archan Misra

Research Collection School Of Computing and Information Systems

This work demonstrates the VGGlass system, which simultaneously interprets human instructions for a target acquisition task and determines the precise 3D positions of both user and the target object. This is achieved by utilizing LiDARs mounted in the infrastructure and a smart glass device worn by the user. Key to our system is the union of LiDAR-based localization termed LiLOC and a multi-modal visual grounding approach termed RealG(2)In-Lite. To demonstrate the system, we use Intel RealSense L515 cameras and a Microsoft HoloLens 2, as the user devices. VGGlass is able to: a) track the user in real-time in a global …

Metaformer Baselines For Vision, Weihao Yu, Chenyang Si, Pan Zhou, Mi Luo, Yichen Zhou, Jiashi Feng, Shuicheng Yan, Xinchao Wang

Research Collection School Of Computing and Information Systems

Abstract—MetaFormer, the abstracted architecture of Transformer, has been found to play a significant role in achieving competitive performance. In this paper, we further explore the capacity of MetaFormer, again, by migrating our focus away from the token mixer design: we introduce several baseline models under MetaFormer using the most basic or common mixers, and demonstrate their gratifying performance. We summarize our observations as follows: (1) MetaFormer ensures solid lower bound of performance. By merely adopting identity mapping as the token mixer, the MetaFormer model, termed IdentityFormer, achieves >80% accuracy on ImageNet-1K. (2) MetaFormer works well with arbitrary token mixers. When …

Rethinking Conversational Agents In The Era Of Large Language Models: Proactivity, Non-Collaborativity, And Beyond, Yang Deng, Wenqiang Lei, Minlie Huang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Conversational systems are designed to offer human users social support or functional services through natural language interactions. Typical conversation researches mainly focus on the response-ability of the system, such as dialogue context understanding and response generation. In the era of large language models (LLMs), LLM-augmented conversational systems showcase exceptional capabilities of responding to user queries for different language tasks. However, as LLMs are trained to follow users' instructions, LLM-augmented conversational systems typically overlook the design of an essential property in intelligent conversations, i.e., goal awareness. In this tutorial, we will introduce the recent advances on the design of agent's awareness …

Residential Metals Abatement Program Investigation Summary Report (Non-Residential Parcels – Indoor Dust) - Silver Bow Montessori School, Environmental Resource Management (Erm)

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Revised Draft Final Quarterly Operations And Maintenance Report Butte Treatment Lagoon System – Third Quarter 2022, Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Residential Metals Abatement Program Investigation Summary Report (Non-Residential Parcels – Indoor Dust) Silver Bow Montessori School, Environmental Protection Agency

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Draft Final Butte Priority Soils Operable Unit (Bpsou) Unreclaimed (Ur) Sites Ur-35 Remedial Action Work Plan (Rawp), Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Optimized Uncertainty Estimation For Vision Transformers: Enhancing Adversarial Robustness And Performance Using Selective Classification, Erik Pautsch, John Li, Silvio Rizzi, George K. Thiruvathukal, Maria Pantoja

Computer Science: Faculty Publications and Other Works

Deep Learning models often exhibit undue confidence when encountering out-of-distribution (OOD) inputs, misclassifying with high confidence. The ideal outcome, in these cases, would be an "I do not know" verdict. We enhance the trustworthiness of our models through selective classification, allowing the model to abstain from making predictions when facing uncertainty. Rather than a singular prediction, the model offers a prediction distribution, enabling users to gauge the model’s trustworthiness and determine the need for human intervention. We assess uncertainty in two baseline models: a Convolutional Neural Network (CNN) and a Vision Transformer (ViT). By leveraging these uncertainty values, we minimize …

Limitations And Possibilities Of Digital Restoration Techniques Using Generative Ai Tools: Reconstituting Antoine François Callet’S Achilles Dragging Hector’S Body Past The Walls Of Troy, Charles O'Brien, James Hutson, Trent Olsen, Jay Ratican

Faculty Scholarship

Digital restoration offers new avenues for conserving historical artworks, yet presents unique challenges. This research delves into the balance between traditional restoration methods and the use of generative artificial intelligence (AI) tools, using Antoine François Callet’s portrayal of Achilles Dragging Hector’s Body Past the Walls of Troy as a case study. The application of Easy Diffusion and Stable Diffusion 2.1 technologies provides insights into AI-driven restoration methods such as inpainting and colorization. Results indicate that while AI can streamline the restoration process, repeated inpainting can compromise the painting’s color quality and detailed features. Furthermore, the AI approach occasionally introduces unintended …

Reimagining Sustainable Urban Communities In Hong Kong, Jeroen Van Ameijde, Sifan Cheng, Junwei Li

Asian Management Insights

Using environmental and social urban design principles to create future new towns. Hong Kong began building New Towns in the 1970s in response to a post-war period of rapid population growth.

Utahns' Perceptions Of Climate Change And Disaster Vulnerabilities, Mufti Nadimul Quamar Ahmed, Jennifer E. Givens, Peter D. Howe, Jessica D. Ulrich-Schad

Utah People and Environment Poll (UPEP)

Climate change increases the frequency and severity of extreme weather events, making people more vulnerable in a variety of ways^1-2. It is essential to determine if individuals believe they are susceptible to the effects of climate change in order to develop effective adaptation strategies.

Climate change has contributed to extreme weather occurrences in Utah in recent years. For instance, in the summer of 2022, there was a severe or extreme drought in all of Utah's counties³. Health effects of drought vary with intensity⁴ and can cause climate related deaths directly and indirectly, such as by …

Correlation Between Scores On The Assessment And Learning In Knowledge Spaces Placement, Preparation, And Learning Test And General Chemistry Course Outcomes For Undergraduate Students At A Public Midsize Master's University, Crystal Kaye Keso

All NMU Master's Theses

This study examined the problem of gateway courses in Science, Technology, Engineering, and Mathematics (STEM), specifically, high-enrollment introductory chemistry courses with high rates of D, F, withdrawal, or incomplete grades. Previous research revealed a correlation between students’ prior mathematics knowledge and introductory chemistry course outcomes. Reports using the Assessment and Learning in Knowledge Spaces Placement, Preparation, and Learning (ALEKS PPL) test were limited in number. This study conducted a non-experimental retrospective correlational analysis between undergraduate students’ ALEKS PPL test scores and introductory chemistry course grades. The study’s theoretical framework was grounded in prerequisite and placement testing theories. The major findings …

Laf: Labeling-Free Model Selection For Automated Deep Neural Network Reusing, Qiang Hu, Yuejun Guo, Xiaofei Xie, Maxime Cordy, Mike Papadakis, Yves Le Traon

Research Collection School Of Computing and Information Systems

pplying deep learning (DL) to science is a new trend in recent years, which leads DL engineering to become an important problem. Although training data preparation, model architecture design, and model training are the normal processes to build DL models, all of them are complex and costly. Therefore, reusing the open-sourced pre-trained model is a practical way to bypass this hurdle for developers. Given a specific task, developers can collect massive pre-trained deep neural networks from public sources for reusing. However, testing the performance (e.g., accuracy and robustness) of multiple deep neural networks (DNNs) and recommending which model should be …

Quantitative, Photocurrent Multidimensional Coherent Spectroscopy, Adam Halaoui

Electronic Theses and Dissertations

Multidimensional coherent spectroscopy (MDCS) is a quickly growing field that has a lot of advantages over more conventional forms of spectroscopy. These advantages all come from the fact that MDCS allows us to get time resolved correlated emission and absorption spectra using very precisely chosen interactions between the density matrix and the excitation laser. MDCS spectra gives the researcher a lot of information that can be extracted purely through qualitative analysis. This is possible because state couplings are entirely separated on the spectra, and once we know how to read the data, we can see how carriers transport in the …

The Use Of Regularization To Detect Racial Inequities In Pay Equity Studies: An Empirical Study And Reflections On Regulation Methods, Christopher M. Peña

Electronic Theses and Dissertations

Since the late 1970s, multiple linear regression has been the preferred method for identifying discrimination in pay. An empirical study on this topic was conducted using quantitative critical methods. A literature review first examined conflicting views on using multiple linear regression in pay equity studies. The review found that multiple linear regression is used so prevalently in pay equity studies because the courts and practitioners have widely accepted it and because of its simplicity and ability to parse multiple sources of variance simultaneously. Commentaries in the literature cautioned about errors in model specification, the use of tainted variables, and the …

Dependence Among Order Statistics For Time-Transformed Exponential Models, Subhash C. Kochar, Fabio Spizzichino

Mathematics and Statistics Faculty Publications and Presentations

Let X₁, ..., X_n be a random vector distributed according to a time-transformed exponential model. This is a special class of exchangeable models, which, in particular, includes multivariate distributions with Schur-constant survival functions. Let for 1 i n, X_i:n denote the corresponding ith-order statistic. We consider the problem of comparing the strength of dependence between any pair of X_i’s with that of the corresponding order statistics. It is in particular proved that for m = 2, ..., n, the dependence of X2:m on X1:m is more than that of X₂ on X …

Groundwater System Characterisation: Fortescue Alluvial Fan, Michael J. Donn, Olga V. Barron, Axel Suckow, Chris Turnadge, John A. Simons, Robert J. Paul, Christopher Schelfhout Dr

Natural resources commissioned reports

This report focuses on groundwater system characterisation in the region north of Newman, based on analysis of pre-existing data and data newly acquired during project activities. Groundwater system characterisation was an important research component supporting the assessment of managed aquifer recharge opportunities, using mine dewatering surplus generated (due to mining below the watertable) at large BHP Billiton Iron Ore operations in the eastern Pilbara mining zone, and aiming to support irrigated agriculture. The assessment area is located north of Ethel Gorge and covers the Upper Fortescue River floodplain and surroundings. The project added much knowledge to this largely ‘data-poor’ region, …

Agricultural Groundcover Update October 2023, Justin Laycock

Natural resources published reports

Summary

• About 98% of the grainbelt had adequate vegetative groundcover (more than 50%) to prevent wind erosion in October 2023. This amount of groundcover is normal at the end of spring and pre-harvest in most areas.
• There was a larger than average area with 51–60% groundcover, and groundcover in these areas is expected to reduce over summer to below 50%.
• About 2% of the grainbelt (293,000 ha) had less than 50% groundcover, which is inadequate to prevent wind erosion. Mullewa to Morawa Ag Soil Zone had the highest risk of wind erosion and 8% of this farmland had inadequate groundcover. …

Interaction Of ΒL- And Γ-Crystallin With Phospholipid Membrane Using Atomic Force Microscopy, Nawal K. Khadka, Preston Hazen, Dieter Haemmerle, Laxman Mainali

Physics Faculty Publications and Presentations

Highly concentrated lens proteins, mostly β- and γ-crystallin, are responsible for maintaining the structure and refractivity of the eye lens. However, with aging and cataract formation, β- and γ-crystallin are associated with the lens membrane or other lens proteins forming high-molecular-weight proteins, which further associate with the lens membrane, leading to light scattering and cataract development. The mechanism by which β- and γ-crystallin are associated with the lens membrane is unknown. This work aims to study the interaction of β- and γ-crystallin with the phospholipid membrane with and without cholesterol (Chol) with the overall goal of understanding the role of …

Spatial Data Management For Green Mobility, Christophe Claramunt, Christine Bassem, Demetrios Zeinalipour-Yazti, Baihua Zheng, Goce Trajcevski, Kristian Torp

Research Collection School Of Computing and Information Systems

While many countries are developing appropriate actions towards a greener future and moving towards adopting sustainable mobility activities, the real-time management and planning of innovative transportation facilities and services in urban environments still require the development of advanced mobile data management infrastructures. Novel green mobility solutions, such as electric, hybrid, solar and hydrogen vehicles, as well as public and gig-based transportation resources are very likely to reduce the carbon footprint. However, their successful implementation still needs efficient spatio-temporal data management resources and applications to provide a clear picture and demonstrate their effectiveness. This paper discusses the major data management challenges, …

Robust Maximum Capture Facility Location Under Random Utility Maximization Models, Tien Thanh Dam, Thuy Anh Ta, Tien Mai

Research Collection School Of Computing and Information Systems

We study a robust version of the maximum capture facility location problem in a competitive market, assuming that each customer chooses among all available facilities according to a random utility maximization (RUM) model. We employ the generalized extreme value (GEV) family of models and assume that the parameters of the RUM model are not given exactly but lie in convex uncertainty sets. The problem is to locate new facilities to maximize the worst-case captured user demand. We show that, interestingly, our robust model preserves the monotonicity and submodularity from its deterministic counterpart, implying that a simple greedy heuristic can guarantee …

Voxelhap: A Toolkit For Constructing Proxies Providing Tactile And Kinesthetic Haptic Feedback In Virtual Reality, M. Feick, C. Biyikli, K. Gani, A. Wittig, Anthony Tang, A. Krüger

Research Collection School Of Computing and Information Systems

Experiencing virtual environments is often limited to abstract interactions with objects. Physical proxies allow users to feel virtual objects, but are often inaccessible. We present the VoxelHap toolkit which enables users to construct highly functional proxy objects using Voxels and Plates. Voxels are blocks with special functionalities that form the core of each physical proxy. Plates increase a proxy’s haptic resolution, such as its shape, texture or weight. Beyond providing physical capabilities to realize haptic sensations, VoxelHap utilizes VR illusion techniques to expand its haptic resolution. We evaluated the capabilities of the VoxelHap toolkit through the construction of a range …

Digitizing The Cultural Capital: Harnessing Digital Humanities For Heritage Preservation In Bujumbura, Burundi, James Hutson, Pace Ellsworth, Matt Ellsworth, Jean Bosco Ntungirimana

Faculty Scholarship

In an era where the erosion of cultural heritage is increasingly prevalent, there exists a critical imperative to explore and implement innovative methods for the preservation and revitalization of cultural identities, as exemplified by the urgent situation in Bujumbura, Burundi. Central to this study is the exploration of innovative digital methodologies for archiving a wide spectrum of cultural artifacts, including both notable and everyday heritage elements, in Bujumbura. Traditional approaches to biographical and historical profiling have predominantly focused on official records and significant events, often neglecting the richness of personal experiences and everyday interactions that substantially shape cultural identities. To …

A Review Of Cyber Attacks On Sensors And Perception Systems In Autonomous Vehicle, Taminul Islam, Md. Alif Sheakh, Anjuman Naher Jui, Omar Sharif, Md Zobaer Hasan

School of Mathematical and Statistical Sciences Faculty Publications and Presentations

Vehicle automation has been in the works for a long time now. Automatic brakes, cruise control, GPS satellite navigation, etc. are all common features seen in today's automobiles. Automation and artificial intelligence breakthroughs are likely to lead to an increase in the usage of automation technologies in cars. Because of this, mankind will be more reliant on computer-controlled equipment and car systems in our daily lives. All major corporations have begun investing in the development of self-driving cars because of the rapid advancement of advanced driver support technologies. However, the level of safety and trustworthiness is still questionable. Imagine what …