Computer Sciences Commons^™

Transformer-Based Deep Learning Prediction Of 10-Degree Humphrey Visual Field Tests From 24-Degree Data, Min Shi, Anagha Lokhande, Yu Tian, Yan Luo, Mohammad Eslami, Saber Kazeminasab, Tobias Elze, Lucy Shen, Louis Pasquale, Sarah Wellik, Carlos Gustavo De Moraes, Jonathan Myers, Nazlee Zebardast, David Friedman, Michael Boland, Mengyu Wang

Wills Eye Hospital Papers

PURPOSE: To predict 10-2 Humphrey visual fields (VFs) from 24-2 VFs and associated non-total deviation features using deep learning.

METHODS: We included 5189 reliable 24-2 and 10-2 VF pairs from 2236 patients, and 28,409 reliable pairs of macular OCT scans and 24-2 VF from 19,527 eyes of 11,560 patients. We developed a transformer-based deep learning model using 52 total deviation values and nine VF test features to predict 68 10-2 total deviation values. The mean absolute error, root mean square error, and the R2 were evaluation metrics. We further evaluated whether the predicted 10-2 VFs can improve the structure-function relationship …

Gradient Wild Bootstrap For Instrumental Variable Quantile Regressions With Weak And Few Clusters, Wenjie Wang, Yichong Zhang

Research Collection School Of Economics

We study the gradient wild bootstrap-based inference for instrumental variable quantile regressions in the framework of a small number of large clusters in which the number of clusters is viewed as fixed, and the number of observations for each cluster diverges to infinity. For the Wald inference, we show that our wild bootstrap Wald test, with or without studentization using the cluster-robust covariance estimator (CRVE), controls size asymptotically up to a small error as long as the parameter of endogenous variable is strongly identified in at least one of the clusters. We further show that the wild bootstrap Wald test …

White Light Specular Reflection Data Augmentation For Polyp Detection, Jose Angel Nunez

Theses and Dissertations

Colorectal cancer is among the deadliest cancers, but fortunately, this type of cancer can be prevented. The best current method of prevention is via detecting the bad polyps in the colon in time. Furthermore, the best method we have available to detect these bad polyps is through colonoscopies. Even though a lot of lives have been saved via these methods, it is still not perfect because of human error. Integrating artificial intelligence into colonoscopy procedures is our next evolution in increasing our prevention of colorectal cancer. Polyp detectors are one of the tools brought by advancements in technology that may …

Comparative Analysis Of Transfer Learning Strategies For Polyp Detection In Colonoscopy Images Using Yolov8, Fabian Vazquez Jr.

Theses and Dissertations

The early detection of polyps during colonoscopy procedures is crucial for preventing colorectal cancer, a leading cause of cancer-related deaths globally. Traditional methods for polyp detection are often time-consuming and prone to human error. This thesis investigates the effectiveness of transfer learning, the process of taking a pre-trained model that was trained on a large dataset and adapting it to a new, but related task, requiring less data and time for training. This research compares whether the YOLOv8 model trained from scratch on a specific polyp dataset is outperformed by transfer learning methods such as utilizing a pretrained model on …

Enabling Iov Communication Through Secure Decentralized Clustering Using Federated Deep Reinforcement Learning, Chandler Scott

Electronic Theses and Dissertations

The Internet of Vehicles (IoV) holds immense potential for revolutionizing transporta- tion systems by facilitating seamless vehicle-to-vehicle and vehicle-to-infrastructure communication. However, challenges such as congestion, pollution, and security per- sist, particularly in rural areas with limited infrastructure. Existing centralized solu- tions are impractical in such environments due to latency and privacy concerns. To address these challenges, we propose a decentralized clustering algorithm enhanced with Federated Deep Reinforcement Learning (FDRL). Our approach enables low- latency communication, competitive packet delivery ratios, and cluster stability while preserving data privacy. Additionally, we introduce a trust-based security framework for IoV environments, integrating a central authority …

Context-Aware Self-Supervised Learning Of Whole Slide Images, Milam Aryal, Nasim Yahyasoltani

Computer Science Faculty Research and Publications

Presenting whole slide images (WSIs) as graph will enable a more efficient and accurate learning framework for cancer diagnosis. Due to the fact that a single WSI consists of billions of pixels and there is a lack of vast annotated datasets required for computational pathology, the problem of learning from WSIs using typical deep learning approaches such as convolutional neural network (CNN) is challenging. Additionally, WSIs downsampling may lead to the loss of data that is essential for cancer detection. A novel two-stage learning technique is presented in this work. Since context, such as topological features in the tumor surroundings, …

Robust Asynchronous Federated Learning With Time-Weighted And Stale Model Aggregation, Yinbin Miao, Ziteng Liu, Xinghua Li, Meng Li, Hongwei Li, Kim-Kwang Raymond Choo, Robert H. Deng

Research Collection School Of Computing and Information Systems

Federated Learning (FL) ensures collaborative learning among multiple clients while maintaining data locally. However, the traditional synchronous FL solutions have lower accuracy and require more communication time in scenarios where most devices drop out during learning. Therefore, we propose an Asynchronous Federated Learning (AsyFL) scheme using time-weighted and stale model aggregation, which effectively solves the problem of poor model performance due to the heterogeneity of devices. Then, we integrate Symmetric Homomorphic Encryption (SHE) into AsyFL to propose Asynchronous Privacy-Preserving Federated Learning (Asy-PPFL), which protects the privacy of clients and achieves lightweight computing. Privacy analysis shows that Asy-PPFL is indistinguishable under …

A Multimodal Foundation Agent For Financial Trading : Tool-Augmented, Diversified, And Generalist, Wentao Zhang, Lingxuan Zhao, Haochong Xia, Shuo Sun, Jiaze Sun, Molei Qin, Xinyi Li, Yuqing Zhao, Yilei Zhao, Xinyu Cai, Longtao Zheng, Xinrun Wang, Bo An

Research Collection School Of Computing and Information Systems

Financial trading is a crucial component of the markets, informed by a multimodal information landscape encompassing news, prices, and Kline charts, and encompasses diverse tasks such as quantitative trading and high-frequency trading with various assets. While advanced AI techniques like deep learning and reinforcement learning are extensively utilized in finance, their application in financial trading tasks often faces challenges due to inadequate handling of multimodal data and limited generalizability across various tasks. To address these challenges, we present FinAgent, a multimodal foundational agent with tool augmentation for financial trading. FinAgent's market intelligence module processes a diverse range of data-numerical, textual, …

Self-Chats From Large Language Models Make Small Emotional Support Chatbot Better, Zhonghua Zheng, Lizi Liao, Yang Deng, Libo Qin, Liqiang Nie

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have shown strong generalization abilities to excel in various tasks, including emotion support conversations. However, deploying such LLMs like GPT-3 (175B parameters) is resource-intensive and challenging at scale. In this study, we utilize LLMs as “Counseling Teacher” to enhance smaller models’ emotion support response abilities, significantly reducing the necessity of scaling up model size. To this end, we first introduce an iterative expansion framework, aiming to prompt the large teacher model to curate an expansive emotion support dialogue dataset. This curated dataset, termed ExTES, encompasses a broad spectrum of scenarios and is crafted with meticulous strategies …

Hierarchical Neural Constructive Solver For Real-World Tsp Scenarios, Yong Liang Goh, Zhiguang Cao, Yining Ma, Yanfei Dong, Mohammed Haroon Dupty, Wee Sun Lee

Research Collection School Of Computing and Information Systems

Existing neural constructive solvers for routing problems have predominantly employed transformer architectures, conceptualizing the route construction as a set-to-sequence learning task. However, their efficacy has primarily been demonstrated on entirely random problem instances that inadequately capture real-world scenarios. In this paper, we introduce realistic Traveling Salesman Problem (TSP) scenarios relevant to industrial settings and derive the following insights: (1) The optimal next node (or city) to visit often lies within proximity to the current node, suggesting the potential benefits of biasing choices based on current locations. (2) Effectively solving the TSP requires robust tracking of unvisited nodes and warrants succinct …

Enhancing Monthly Streamflow Prediction Using Meteorological Factors And Machine Learning Models In The Upper Colorado River Basin, Saichand Thota

All Graduate Theses and Dissertations, Fall 2023 to Present

Understanding and predicting streamflow along river basins is vital for planning future developments and ensuring safety, especially with climate change challenges. Our study focused on forecasting streamflow at Lees Ferry, a key location along the Colorado River in the Upper Colorado River Basin. We employed four machine learning models - Random Forest Regression, Long short-term memory, Gated Recurrent Unit, and Seasonal Auto-Regressive Integrated Moving Average; and combined historical streamflow data with meteorological factors such as snow water equivalent, temperature, and precipitation. Our analysis spanned 30 years of data from 1991 to 2020.

Our findings revealed that the Random Forest Regression …

Fishing Vessel Detection In Exclusive Economic Zones From Low Earth Orbit Satellites With Power And Computational Constraints, Kyler E. Nelson

All Graduate Theses and Dissertations, Fall 2023 to Present

Illegal fishing activities pose a significant threat to the sustainability of marine ecosystems and the economies and societies which rely on them. Detection of fishing vessels engaging in illegal activity is difficult, as many ships engaging in such activity actively avoid detection through radio systems used for maritime traffic monitoring. Satellite imagery provides a promising means for detecting fishing vessels, though designing an effective system is difficult due to limited availability of labeled image datasets of fishing vessels. This research proposes a system to detect illegal fishing activity through the use of a low-power ship detection satellite and proposes a …

Exploring The Integration Of Blockchain In Iot Use Cases: Challenges And Opportunities, Ivannah George

Electronic Theses, Projects, and Dissertations

Blockchain and The Internet of Things (IoT) is a significant paradigm which has gained traction in today’s digital age as two complimentary technologies. The combination of IoT's connectivity with blockchain's security creates new opportunities and solves problems associated with centralized systems. This culminating project aims to delve deeper into the integration of blockchain technology in IoT applications based on select use cases to uncover potential benefits and significant challenges of blockchain integration across different sectors. The research objectives to be addressed are: (RO1) How emerging vulnerabilities manifest in the implementation of blockchain within current IoT ecosystems. (RO2) How current opportunities …

High Prevalence Of Artifacts In Optical Coherence Tomography With Adequate Signal Strength, Wei-Chun Lin, Aaron Coyner, Charles Amankwa, Abigail Lucero, Gadi Wollstein, Joel Schuman, Hiroshi Ishikawa

Wills Eye Hospital Papers

PURPOSE: This study aims to investigate the prevalence of artifacts in optical coherence tomography (OCT) images with acceptable signal strength and evaluate the performance of supervised deep learning models in improving OCT image quality assessment.

METHODS: We conducted a retrospective study on 4555 OCT images from 546 patients, with each image having an acceptable signal strength (≥6). A comprehensive analysis of prevalent OCT artifacts was performed, and five pretrained convolutional neural network models were trained and tested to infer images based on quality.

RESULTS: Our results showed a high prevalence of artifacts in OCT images with acceptable signal strength. Approximately …

Clamber: A Benchmark Of Identifying And Clarifying Ambiguous Information Needs In Large Language Models, Tong Zhang, Peixin Qin, Yang Deng, Chen Huang, Wenqiang Lei, Junhong Liu, Dingnan Jin, Hongru Liang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Large language models (LLMs) are increasingly used to meet user information needs, but their effectiveness in dealing with user queries that contain various types of ambiguity remains unknown, ultimately risking user trust and satisfaction. To this end, we introduce CLAMBER, a benchmark for evaluating LLMs using a well-organized taxonomy. Building upon the taxonomy, we construct 12K high-quality data to assess the strengths, weaknesses, and potential risks of various off-the-shelf LLMs.Our findings indicate the limited practical utility of current LLMs in identifying and clarifying ambiguous user queries, even enhanced by chain-of-thought (CoT) and few-shot prompting. These techniques may result in overconfidence …

Analyzing Temporal Complex Events With Large Language Models? A Benchmark Towards Temporal, Long Context Understanding, Zhihan Zhang, Yixin Cao, Chenchen Ye, Ma. Yunshan, Lizi Liao, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

The digital landscape is rapidly evolving with an ever-increasing volume of online news, emphasizing the need for swift and precise analysis of complex events.We refer to the complex events composed of many news articles over an extended period as Temporal Complex Event (TCE). This paper proposes a novel approach using Large Language Models (LLMs) to systematically extract and analyze the event chain within TCE, characterized by their key points and timestamps. We establish a benchmark, named TCELongBench, to evaluate the proficiency of LLMs in handling temporal dynamics and understanding extensive text. This benchmark encompasses three distinct tasks - reading comprehension, …

Larp: Language Audio Relational Pre‑Training For Cold‑Start Playlist Continuation, Rebecca Salganik, Xiaohao Liu, Yunshan Ma, Jian Kang, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

As online music consumption increasingly shifts towards playlist-based listening, the task of playlist continuation, in which an algorithm suggests songs to extend a playlist in a personalized and musically cohesive manner, has become vital to the success of music streaming services. Currently, many existing playlist continuation approaches rely on collaborative filtering methods to perform their recommendations. However, such methods will struggle to recommend songs that lack interaction data, an issue known as the cold-start problem. Current approaches to this challenge design complex mechanisms for extracting relational signals from sparse collaborative signals and integrating them into content representations. However, these approaches …

Divergence Measures And Aggregation Operators For Single-Valued Neutrosophic Sets With Applications In Decision-Making Problems, Surender Singh, Sonam Sharma

Neutrosophic Systems with Applications

Single-valued neutrosophic sets (SVNSs) facilitate the representation of uncertain information more extensively than conventional methods. The study of divergence measures of SVNSs is important due to their applications in different areas like multi-criteria decision-making (MCDM), pattern recognition, cluster analysis, machine learning, etc., In this paper, we introduce a divergence measure for SVNSs. The suggested divergence measure is applied to cluster analysis for the classification of imprecise data. For establishing the reasonability and advantage of the suggested divergence measure in a clustering problem over the existing measures, a comparative assessment is also presented. Furthermore, we introduce, an inferior ratio method for …

Deep Representation Learning For Time Series Forecasting, Gerald Woo

Dissertations and Theses Collection (Open Access)

Time series forecasting has critical applications across business and scien- tific domains, such as demand forecasting, capacity planning and management, and anomaly detection. Being able to predict the future yields immense value, allowing us to make downstream decisions with more confidence. Deep learning for time series forecasting is a burgeoning area of research, moving away from simple linear models found in classical time series analysis literature, towards more expressive, data hungry neural network architectures.

In this thesis, we develop methods leveraging deep representation learning for time series forecasting, from exploring neural network architecture designs which encode inductive biases specific to …

An Efficient Neutrosophic Approach For Evaluating Possible Industry 5.0 Enablers In Consumer Electronics: A Case Study, Mai Mohamed, Asmaa Elsayed, Bilal Arain, Jun Ye

Neutrosophic Systems with Applications

With the use of cutting-edge technologies like artificial intelligence (AI), robotics, and the Internet of Things (IoT), Industry 5.0 represents a breakthrough move towards a sustainable and human-centered industrial future. Industry 5.0 endeavors to transform industries such as consumer electronics by emphasizing sustainability and collaboration, in contrast to its predecessors, who only concentrated on automation and efficiency. Along with improved manufacturing efficiency and product innovation, this change in the consumer electronics sector also redefines the human-machine interaction. This paper proposes a novel hybrid integrating model that combines the Entropy Weight Method (EWM), Best-Worst Method (BWM), and an acronym in Portuguese …

Interpretation Models For Prostate Lesion: Detecting, Explaining, And Understanding., Mehmet Akif Gulum

Electronic Theses and Dissertations

Prostate cancer is a major public health concern, affecting millions of men worldwide. While early detection and treatment of prostate cancer is critical for improving patient outcomes, the detection of prostate lesions is even more important for timely intervention and management of the disease. Prostate lesions are abnormal growths or lumps within the prostate gland, which may or may not be cancerous. The timely detection and accurate diagnosis of prostate lesions is crucial for effective treatment and management of the disease. In recent years, deep learning models have shown promise in accurately detecting and characterizing prostate lesions using advanced imaging …

Offensive Content Detection In Online Social Platforms, Ebuka Okpala

All Dissertations

Online social platforms enable users to connect with large, diverse audiences and the ability for a message or content to flow from one user to another user, user to followers, followers to user, and followers to followers. Of course, the advantages of this are apparent, and the dangers are also clearly obvious. The user-generated content could be abusive, offensive, or hateful to other users, possibly leading to adverse health effects or offline harm. As more of society's public discourse and interaction move online and these platforms grow and increase their reach, it is inherently important to protect the safety of …

The Health Belief Model And Phishing: Determinants Of Preventative Security Behaviors, Jie Du, Andrew Kalafut, Gregory Schymik

Open Access Publishing Support Funded Articles

Email is frequently the attack vector of choice for hackers and is a large concern for campus IT organizations. This paper attempts to gain insight into what drives the email security behaviors of students, faculty, and staff at one midwestern public, master’s granting university. The survey relies on the health belief model as its theoretical basis and measures eight constructs including email security behavior, perceived barriers to practice, self-efficacy, cues to action, prior security experience, perceived vulnerability, perceived benefits, and perceived severity. Barriers to practice, self-efficacy, vulnerability, benefits, and prior experience variables were found to be significant determinants of self-reported …

Physics-Informed Machine Learning Methods For Inverse Design Of Multi-Phase Materials With Targeted Mechanical Properties, Yunpeng Wu

All Dissertations

Advances in machine learning algorithms and applications have significantly enhanced engineering inverse design capabilities. This work focuses on the machine learning-based inverse design of material microstructures with targeted linear and nonlinear mechanical properties. It involves developing and applying predictive and generative physics-informed neural networks for both 2D and 3D multiphase materials.

The first investigation aims to develop a machine learning method for the inverse design of 2D multiphase materials, particularly porous materials. We first develop machine learning methods to understand the implicit relationship between a material's microstructure and its mechanical behavior. Specifically, we use ResNet-based models to predict the elastic …

Remote Onboarding Of Software Developers: Leveraging Virtual Reality And Ai Tools, James Dominic

All Dissertations

Software development teams add newcomers to accommodate the increasing demand, complexity of software solutions, and turnover. Onboarding newcomers is expensive and error-prone. It can take up to three years for a newcomer to become an expert on a project. Onboarding techniques described in the current literature focus on collocated teams. As more teams are adopting remote and distributed team structures, I address this research gap in understanding remote onboarding for software developers. I present my research on the use of Virtual Reality (VR) for remote software developer onboarding. I discuss a VR remote pair programming environment. With positive outcomes, pair …

Ensuring The Privacy Compliance Of Voice Personal Assistant Applications, Song Liao

All Dissertations

Voice Personal Assistants (VPA) such as Amazon Alexa and Google Assistant are quickly and seamlessly integrating into people’s daily lives. Meanwhile, the increased reliance on VPA services raises privacy concerns, such as the leakage of private conversations and sensitive information. Privacy policies play an important role in addressing users’ privacy concerns and developers are required to provide privacy policies to disclose their apps’ data practices. In addition, voice apps targeting users in European countries are required to comply with the GDPR (General Data Protection Regulation). However, little is known about whether these privacy policies are informative and trustworthy on emerging …

Genomic Data Science Approaches For Understanding Human Diseases, Snehal Shah

All Dissertations

The intricate interplay of genetic predisposition, environmental influences, and lifestyle acts as the multifactorial landscape of diseases. Understanding this complexity presents a significant challenge. Molecular insights into disease mechanisms, particularly the interactions of DNA, RNA, and proteins with environmental and lifestyle factors, have revolutionized disease diagnosis, prognosis, and treatment. High-throughput technologies, such as next-generation sequencing, generate large amounts of molecular data, holding a wealth of knowledge. These datasets unveil the roles of genes and their interactions with various factors through analysis, shedding light on previously unknown molecular mechanisms underlying disease pathogenesis. Furthermore, they facilitate the discovery of biomarkers crucial for …

We Train Ai, Why Not Humans, Too? An Exploration Of Human-Ai Team Training For Future Workplace Viability, Caitlin M. Lancaster

All Dissertations

The integration of Artificial Intelligence (AI) in the workforce is transforming team dynamics, leading to the emergence of Human-AI Teams (HATs). These teams offer opportunities to capitalize on human strengths with AI's prowess, offering significant opportunities for innovation and efficiency. Effective HAT functioning requires aligning human expectations with AI capabilities and bridging knowledge gaps between teammates. Despite this potential, key integration challenges remain, such as developing shared mental models, addressing skill limitations, and overcoming negative AI perceptions. Existing training efforts often apply human-human teaming principles directly to HATs, overlooking AI's role as a teammate and limiting the development of HAT-specific …

Segac: Sample Efficient Generalized Actor Critic For The Stochastic On-Time Arrival Problem, Honglian Guo, Zhi He, Wenda Sheng, Zhiguang Cao, Yingjie Zhou, Weinan Gao

Research Collection School Of Computing and Information Systems

This paper studies the problem in transportation networks and introduces a novel reinforcement learning-based algorithm, namely. Different from almost all canonical sota solutions, which are usually computationally expensive and lack generalizability to unforeseen destination nodes, segac offers the following appealing characteristics. segac updates the ego vehicle’s navigation policy in a sample efficient manner, reduces the variance of both value network and policy network during training, and is automatically adaptive to new destinations. Furthermore, the pre-trained segac policy network enables its real-time decision-making ability within seconds, outperforming state-of-the-art sota algorithms in simulations across various transportation networks. We also successfully deploy segac …

Ee-Lce: An Event Extraction Framework Based On Llm-Generated Cot Explanation, Yanhua Yu, Yuanlong Wang, Yunshan Ma, Jie Li, Kangkang Lu, Zhiyong Huang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Generative models have been widely used in event extraction. However, the interpretability of event extraction has not been fully investigated. In this paper, we propose an Event Extraction framework based on LLM-generated CoT Explanation EE-LCE, which can generate chain-of-thought-style (CoT-style) explanations for events. To this end, we provide each sample of event datasets with an explanation of the reasoning process using a large language model (LLM) GPT-3.5, and fine-tune the Flan-T5 lightweight language model (LM) supervised by the augmented dataset, enhancing both interpretability and performance of the event extraction. Moreover, we use a prefix tree (trie) to normalize the decoding …