Computer Sciences Commons^™

Evaluation Of An End-To-End Radiotherapy Treatment Planning Pipeline For Prostate Cancer, Mohammad Daniel El Basha, Court Laurence, Carlos Eduardo Cardenas, Julianne Pollard-Larkin, Steven Frank, David T. Fuentes, Falk Poenisch, Zhiqian H. Yu

Dissertations and Theses (Open Access)

Radiation treatment planning is a crucial and time-intensive process in radiation therapy. This planning involves carefully designing a treatment regimen tailored to a patient’s specific condition, including the type, location, and size of the tumor with reference to surrounding healthy tissues. For prostate cancer, this tumor may be either local, locally advanced with extracapsular involvement, or extend into the pelvic lymph node chain. Automating essential parts of this process would allow for the rapid development of effective treatment plans and better plan optimization to enhance tumor control for better outcomes.

The first objective of this work, to automate the treatment …

Developing Machine Learning Agency Among Youth: Characterizing Youth Critical Use, Examination, And Production Of Machine Learning Applications, Ibrahim Oluwajoba Adisa

All Dissertations

This study explores how middle school-aged youths at an afterschool center utilized, examined, and produced AI applications for social good with the support of adults and peers. The study employs a qualitative single case study design. It uses thematic analysis and quantitative ethnography methods to analyze data from multiple sources, including field notes, interviews, focus groups, story completions, video recordings, and artifacts. Findings indicated that engaging youths in critical exploration of AI tools enhanced their ability to design interest-based AI applications that provide solutions for healthcare problems, security, and accessibility. Moreover, the computational thinking practices that youth engaged in increased …

The Human Side Of Adaptive Autonomy: Design Considerations For Adaptive Autonomous Teammates, Allyson Hauptman

All Dissertations

Ground-breaking advances in artificial intelligence (AI) have led to the possibility of AI agents operating not just as useful tools for teams, but also as full-fledged team members with unique, interdependent roles. This possibility is fueled by the human desire to create more and more autonomous systems that possess computational powers beyond human capability and the promise of increasing the productivity and efficiency of human teams dramatically. Yet, for all the promise and potential of these human-AI teams, the inclusion of AI teammates presents several challenges and concerns for both teaming and human-centered AI.

An important part of teaming is …

Artificial Intelligence's Ability To Detect Online Predators, Olatilewa Osifeso

Electronic Theses, Projects, and Dissertations

Online child predators pose a danger to children who use the Internet. Children fall victim to online predators at an alarming rate, based on the data from the National Center of Missing and Exploited Children. When making online profiles and joining websites, you only need a name, an email and a password without identity verification. Studies have shown that online predators use a variety of methods and tools to manipulate and exploit children, such as blackmail, coercion, flattery, and deception. These issues have created an opportunity for skilled online predators to have fewer obstacles when it comes to contacting and …

An Empirical Study On The Efficacy Of Llm-Powered Chatbots In Basic Information Retrieval Tasks, Naja Faysal

Electronic Theses, Projects, and Dissertations

The rise of conversational user interfaces (CUIs) powered by large language models (LLMs) is transforming human-computer interaction. This study evaluates the efficacy of LLM-powered chatbots, trained on website data, compared to browsing websites for finding information about organizations across diverse sectors. A within-subjects experiment with 165 participants was conducted, involving similar information retrieval (IR) tasks using both websites (GUIs) and chatbots (CUIs). The research questions are: (Q1) Which interface helps users find information faster: LLM chatbots or websites? (Q2) Which interface helps users find more accurate information: LLM chatbots or websites?. The findings are: (Q1) Participants found information significantly faster …

Code For Care: Hypertension Prediction In Women Aged 18-39 Years, Kruti Sheth

Electronic Theses, Projects, and Dissertations

The longstanding prevalence of hypertension, often undiagnosed, poses significant risks of severe chronic and cardiovascular complications if left untreated. This study investigated the causes and underlying risks of hypertension in females aged between 18-39 years. The research questions were: (Q1.) What factors affect the occurrence of hypertension in females aged 18-39 years? (Q2.) What machine learning algorithms are suited for effectively predicting hypertension? (Q3.) How can SHAP values be leveraged to analyze the factors from model outputs? The findings are: (Q1.) Performing Feature selection using binary classification Logistic regression algorithm reveals an array of 30 most influential factors at an …

Sliding Markov Decision Processes For Dynamic Task Planning On Uncrewed Aerial Vehicles, Trent Wiens

Department of Mechanical and Materials Engineering: Dissertations, Theses, and Student Research

Mission and flight planning problems for uncrewed aircraft systems (UASs) are typically large and complex in space and computational requirements. With enough time and computing resources, some of these problems may be solvable offline and then executed during flight. In dynamic or uncertain environments, however, the mission may require online adaptation and replanning. In this work, we will discuss methods of creating MDPs for online applications, and a method of using a sliding resolution and receding horizon approach to build and solve Markov Decision Processes (MDPs) in practical planing applications for UASs. In this strategy, called a Sliding Markov Decision …

Artificial Intelligence-Powered Assessment Of Pathologic Response To Neoadjuvant Atezolizumab In Patients With Nsclc: Results From The Lcmc3 Study, Sanja Dacic, William D Travis, Jennifer M Giltnane, Filip Kos, John Abel, Stephanie Hilz, Junya Fujimoto, Lynette Sholl, Jon Ritter, Farah Khalil, Yi Liu, Amaro Taylor-Weiner, Murray Resnick, Hui Yu, Fred R Hirsch, Paul A Bunn, David P Carbone, Valerie Rusch, David J Kwiatkowski, Bruce E Johnson, Jay M Lee, Stephanie R Hennek, Ilan Wapinski, Alan Nicholas, Ann Johnson, Katja Schulze, Mark G Kris, Ignacio I Wistuba

Faculty, Staff and Student Publications

Introduction: Pathologic response (PathR) by histopathologic assessment of resected specimens may be an early clinical end point associated with long-term outcomes with neoadjuvant therapy. Digital pathology may improve the efficiency and precision of PathR assessment. LCMC3 (NCT02927301) evaluated neoadjuvant atezolizumab in patients with resectable NSCLC and reported a 20% major PathR rate.

Methods: We determined PathR in primary tumor resection specimens using guidelines-based visual techniques and developed a convolutional neural network model using the same criteria to digitally measure the percent viable tumor on whole-slide images. Concordance was evaluated between visual determination of percent viable tumor (n = …

Identifying Temporomandibular Disorder Morphological Risk Factors Via Explainable Deep Learning And Multiscale Biomechanical Modeling, Shuchun Sun

All Dissertations

Clarifying multifactorial musculoskeletal disorder etiologies supports risk analysis and development of targeted prevention and treatment modalities. Deep learning enables comprehensive risk factor identification through systematic analysis of disease datasets but does not provide sufficient context for mechanistic understanding, limiting clinical applicability for etiological investigations. Conversely, multiscale biomechanical modeling can evaluate mechanistic etiology within the relevant biomechanical and physiological context. We propose a hybrid approach combining 3D explainable deep learning and multiscale biomechanical modeling; we applied this approach to investigate temporomandibular joint (TMJ) disorder etiology by systematically identifying risk factors and elucidating mechanistic relationships between risk factors and TMJ biomechanics and …

Robust And Trustworthy Deep Learning: Attacks, Defenses And Designs, Bingyin Zhao

All Dissertations

Deep neural networks (DNNs) have achieved unprecedented success in many fields. However, robustness and trustworthiness have become emerging concerns since DNNs are vulnerable to various attacks and susceptible to data distributional shifts. Attacks such as data poisoning and out-of-distribution scenarios such as natural corruption significantly undermine the performance and robustness of DNNs in model training and inference and impose uncertainty and insecurity on the deployment in real-world applications. Thus, it is crucial to investigate threats and challenges against deep neural networks, develop corresponding countermeasures, and dig into design tactics to secure their safety and reliability. The works investigated in this …

Representation Learning For Generative Models With Applications To Healthcare, Astronautics, And Aviation, Van Minh Nguyen

Theses and Dissertations

This dissertation explores applications of representation learning and generative models to challenges in healthcare, astronautics, and aviation.

The first part investigates the use of Generative Adversarial Networks (GANs) to synthesize realistic electronic health record (EHR) data. An initial attempt at training a GAN on the MIMIC-IV dataset encountered stability and convergence issues, motivating a deeper study of 1-Lipschitz regularization techniques for Auxiliary Classifier GANs (AC-GANs). An extensive ablation study on the CIFAR-10 dataset found that Spectral Normalization is key for AC-GAN stability and performance, while Weight Clipping fails to converge without Spectral Normalization. Analysis of the training dynamics provided further …

Deep Learning In Indus Valley Script Digitization, Deva Munikanta Reddy Atturu

Theses and Dissertations

This research introduces ASR-net(Ancient Script Recognition), a groundbreaking system that automatically digitizes ancient Indus seals by converting them into coded text, similar to Optical Character Recognition for modern languages. ASR-net, with an 95% success rate in identifying individual symbols, aims to address the crucial need for automated techniques in deciphering the enigmatic Indus script. Initially Yolov3 is utilized to create the bounding boxes around each graphemes present in the Indus Valley Seal. In addition to that we created M-net(Mahadevan) model to encode the graphemes. Beyond digitization, the paper proposes a new research challenge called the Motif Identification Problem (MIP) related …

Learning Adversarial Semantic Embeddings For Zero-Shot Recognition In Open Worlds, Tianqi Li, Guansong Pang, Xiao Bai, Jin Zheng, Lei Zhou, Xin Ning

Research Collection School Of Computing and Information Systems

Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with only their side semantic information presented during training. It cannot handle real-life, open-world scenarios where there are test samples of unknown classes for which neither samples (e.g., images) nor their side semantic information is known during training. Open-Set Recognition (OSR) is dedicated to addressing the unknown class issue, but existing OSR methods are not designed to model the semantic information of the unseen classes. To tackle this combined ZSL and OSR problem, we consider the case of “Zero-Shot Open-Set Recognition” (ZS-OSR), where a model is trained under the ZSL …

Diffusion-Based Negative Sampling On Graphs For Link Prediction, Yuan Fang, Yuan Fang

Research Collection School Of Computing and Information Systems

Link prediction is a fundamental task for graph analysis with important applications on the Web, such as social network analysis and recommendation systems, etc. Modern graph link prediction methods often employ a contrastive approach to learn robust node representations, where negative sampling is pivotal. Typical negative sampling methods aim to retrieve hard examples based on either predefined heuristics or automatic adversarial approaches, which might be inflexible or difficult to control. Furthermore, in the context of link prediction, most previous methods sample negative nodes from existing substructures of the graph, missing out on potentially more optimal samples in the latent space. …

On The Feasibility Of Simple Transformer For Dynamic Graph Modeling, Yuxia Wu, Yuan Fang, Lizi Liao

Research Collection School Of Computing and Information Systems

Dynamic graph modeling is crucial for understanding complex structures in web graphs, spanning applications in social networks, recommender systems, and more. Most existing methods primarily emphasize structural dependencies and their temporal changes. However, these approaches often overlook detailed temporal aspects or struggle with long-term dependencies. Furthermore, many solutions overly complicate the process by emphasizing intricate module designs to capture dynamic evolutions. In this work, we harness the strength of the Transformer’s self-attention mechanism, known for adeptly handling long-range dependencies in sequence modeling. Our approach offers a simple Transformer model, called SimpleDyG, tailored for dynamic graph modeling without complex modifications. We …

Enhancing Visual Grounding In Vision-Language Pre-Training With Position-Guided Text Prompts, Alex Jinpeng Wang, Pan Zhou, Mike Zheng Shou, Shuicheng Yan

Research Collection School Of Computing and Information Systems

Vision-Language Pre-Training (VLP) has demonstrated remarkable potential in aligning image and text pairs, paving the way for a wide range of cross-modal learning tasks. Nevertheless, we have observed that VLP models often fall short in terms of visual grounding and localization capabilities, which are crucial for many downstream tasks, such as visual reasoning. In response, we introduce a novel Position-guided Text Prompt ( PTP ) paradigm to bolster the visual grounding abilities of cross-modal models trained with VLP. In the VLP phase, PTP divides an image into N x N blocks and employs a widely-used object detector to identify objects …

Optimization Pump As Turbine Coupled To A Self-Excited Induction Generator Using Multi-Objective Genetic Algorithm, Emanuel J. Nyirenda

Tanzania Journal of Engineering and Technology (TJET)

As a way of accelerating the deployment of affordable and clean renewable energy generation technologies, applying a pump working as a turbine coupled to a self-excited induction generator is gaining popularity in various areas including energy recovery and micro hydro systems. However, it is currently challenging to predict the performance of the PAT-SEIG system and there is no agreed-upon rule on the selection of the appropriate system to be installed at a particular site. This paper has presented multi-objective optimization to select the best operating point of the PAT-SEIG system. The results show that the peak efficiencies for the PAT …

Assessment Of Risk Factors Related To Body Pain Complaints In Tanzania Construction Industry, Fatma K. Mohamed

Tanzania Journal of Engineering and Technology (TJET)

The construction industry is associated with risks that can result in musculoskeletal diseases. Although young male workers who are presumed to be healthy dominate the industry in Tanzania, body pain complaints have been widely reported. The aim of this study is to assess the prevalence and causes of body pains in workers. A cross-sectional study involving 396 workers was conducted. A chi square test was used for testing association of independent categorical variables and binary logistic regression analysis was used to determine predictors for body pain complaints. The results show that all study participants complained of at least one form …

Evaluating Introductory Computer Science Labs In The Presence Of Ai Tools, Nicholas Snow, Devin Chaimberlain, Abigail Pitcairn, Benjamin Sweeney

Thinking Matters Symposium

This study explores the resistance of introductory computer science lab assignments to “shortcutting” by generative AI tools, such as ChatGPT. By analyzing the work of three distinct student personas on these assignments, we identified key characteristics of language and structure that influence an assignment's vulnerability to AI abuse. Based on these insights, we propose strategies for educators to adapt labs to both counteract AI shortcutting and encourage productive uses of AI.

Machine Learning-Based Gps Jamming And Spoofing Detection, Alberto Squatrito

Doctoral Dissertations and Master's Theses

The increasing reliance on Global Positioning System (GPS) technology across various sectors has exposed vulnerabilities to malicious attacks, particularly GPS jamming and spoofing. This thesis presents an analysis into detection and mitigation strategies for enhancing the resilience of GPS receivers against jamming and spoofing attacks. The research entails the development of a simulated GPS signal and a receiver model to accurately decode and extract information from simulated GPS signals. The study implements the generation of jammed and spoofed signals to emulate potential threats faced by GPS receivers in practical settings. The core innovation lies in the integration of machine learning …

Artificial Intelligence And Film: A Journey In Public Perception From 1960 To The Present Day, Kayla Anderson, Andrew Roggeman, Joseph Fuller

Celebrating Scholarship and Creativity Day (2018-)

An analysis of accomplishments in film from the 1960s-2020s that feature Artificial Intelligence to give a full picture of how public perception has changed towards these technologies over time, supplemented by historical and technological context.

Hello, World., Elliot Cetinski, Evan Chartock, Olivia Cross, Kiran Drew, Kaya Eller, Ben Little, Joey Nolan, Spencer Toth, Sophie Wahl-Taylor, Sadie Walker, Destiny Young, Annie Zulick

Theater and Dance Presentations

This project works to theatrically represent the current state of Artificial Intelligence (AI), as well as its benefits and drawbacks, in the style of the Living Newspaper. Originating from a Great Depression-era job program, the Living Newspaper sought to take headlines and present them onstage for a poignant and contemporary social critique. This work does the same, melding different angles of the AI debate into a single production that emphasizes the rapidly progressing state of modern AI technology and the need for humans to consider the impacts such technologies will have. Furthermore, it asks the audience to question their position …

Editorials For Special Topic "Artificial Intelligence And Future Society"

Bulletin of Chinese Academy of Sciences (Chinese Version)

No abstract provided.

Social Order In Age Of Artificial Intelligence, Yongnian Zheng

Bulletin of Chinese Academy of Sciences (Chinese Version)

While the rapid development of artificial intelligence is empowering society, it is also posing serious threats to the continuation of the traditional social order. The "de-intellectualization" function of AI has given rise to the phenomenon of "artificial ignorance", referring to the self-inflicted intellectual harm caused by the uncontrolled and excessive misuse of AI-related tools, thus causing a profound impact on the social order. The technical structural characteristics and governance structural characteristics of AI contributed to the emergence of the phenomenon of "artificial ignorance". The technical structural characteristics of AI can be summarized as highly concentrated capabilities, highly centralized control, highly …

Impact Analysis Of Artificial Intelligence Technology On Employment And Income In China, Yan Lu, Lincui Gui

Bulletin of Chinese Academy of Sciences (Chinese Version)

With the continuous development of artificial intelligence technology, employment and income in China will undergo some new changes. It is necessary to explore the impact of artificial intelligence technology on employment and income distribution. The study finds that in terms of employment, the impact of artificial intelligence includes redefining the number and nature of jobs, affecting work patterns and work skills, and possibly triggering structural imbalances between supply and demand in the labor market, leading to employment inequality, increasing employment risks. In term of income distribution, artificial intelligence technology has a heterogeneous impact on the initial distribution of different fields, …

Open Governance And Innovation Directions Regulation: Research On Institutional Mechanisms For Promoting Development Of Artificial General Intelligence, Yuhao Jiang, Xinyi Zhang, Mingjie Dai

Bulletin of Chinese Academy of Sciences (Chinese Version)

In the field of artificial intelligence development, there is still a certain gap between China and the United States. The uncertain future of artificial general intelligence (AGI) decides that China should not only implement the "catch-up" strategy. Artificial intelligence is not a ‘linear innovation' development path, but there is overlap between basic research, applied research, and industrial transformation. This feature of innovation shows that diversified exploration can be realized based on tracking of international frontiers, breakthrough of basic research, and satisfaction of diverse application needs. China needs to adhere to the promotion of open governance, and regulate innovation directions of …

Research On Data Security And International Governance Cooperation Framework In Era Of Artificial Intelligence, Yuanyuan Wei

Bulletin of Chinese Academy of Sciences (Chinese Version)

This study explores the international cooperation framework for data security governance and its implementation pathways from a global governance perspective. First, the study defines the concepts of data security and governance, emphasizing that the core objective of data governance is to ensure the secure flow and effective utilization of data. Second, it analyzes the current fragmentation of the global data governance system, revealing its development trends and challenges under the influence of geopolitics, particularly the tensions and collaborations in key areas such as cross-border data flows. Based on this analysis, the study proposes the concept of the "Embedded Digital Community …

Study On Constraints And Policy Responses For Production And Circulation Of Ai Training Data In China, Tao Lin

Bulletin of Chinese Academy of Sciences (Chinese Version)

The quantity and quality of training data are critical to the performance of artificial intelligence (AI) models. However, in China, the production of training data is hindered by issues such as insufficient quantity, low quality, and fragmented distribution, compounded by limitations stemming from commercial ecosystems, regulatory frameworks, and restricted development and utilization of public data. To address these challenges, this study proposes several policy recommendations, including incentivizing research institutions to generate open-source datasets, fostering AI application scenarios, adopting a "loose-in, focus-out" regulatory approach, introducing intellectual property exemption provisions, refining personal information protection guidelines, and expediting the establishment of a unified …

Venture Capital And Its Role In Facilitating Better Development In China's Artificial Intelligence Industry, Randong Yuan

Bulletin of Chinese Academy of Sciences (Chinese Version)

The venture capital (VC) industry plays a crucial role in advancing the development of the artificial intelligence (AI) sector. As a key bridge between technological innovation and industrialization, VC not only provides financial support to AI startups but also empowers them in strategic planning, technological research and development, and market expansion. However, China's VC industry currently faces several challenges in supporting AI development, including an imbalance in the roles of state-owned and private capital, a short-term investment mindset, and the cyclical phenomenon of "herding" and abrupt market exits. These issues hinder the growth trajectories of Chinese AI enterprises and constrain …

New System For Mobilizing Resources Nationwide To Promote Leapfrog Development Of Innovation Ecosystem Of Artificial Intelligence Enterprises: Mechanisms, Problems And Strategies, Yang Mei, Hao Niu, Han Jiang

Bulletin of Chinese Academy of Sciences (Chinese Version)

Facing the unpredictable new features of top-down AI technological innovation and the new requirements on functions, this study proposes to re-examine the technological innovation of AI at the enterprise level from the perspective of the "a new system for mobilizing the resources nationwide" and with the enterprise innovation ecosystem as the carrier. On the basis of explaining the elements and operation logic of the new system at the enterprise level, compared to the "implicit national system" of the US, this study preliminarily compares the new system of AI in China and that in the US. It is proposed that the …