Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Engineering (503)
- Information Security (212)
- Artificial Intelligence and Robotics (183)
- Computer Engineering (147)
- Software Engineering (144)
-
- Databases and Information Systems (129)
- Electrical and Computer Engineering (127)
- Theory and Algorithms (122)
- Graphics and Human Computer Interfaces (98)
- Operations Research, Systems Engineering and Industrial Engineering (88)
- Aerospace Engineering (56)
- Digital Communications and Networking (52)
- Signal Processing (47)
- Business (41)
- Data Science (41)
- Numerical Analysis and Scientific Computing (41)
- Operational Research (37)
- Other Computer Sciences (35)
- Physics (32)
- Social and Behavioral Sciences (31)
- Aviation (29)
- OS and Networks (29)
- Cybersecurity (25)
- Applied Mathematics (24)
- Systems Architecture (24)
- Education (23)
- Programming Languages and Compilers (22)
- Medicine and Health Sciences (20)
- Institution
-
- Air Force Institute of Technology (1062)
- Brigham Young University (398)
- University for Business and Technology in Kosovo (393)
- Florida Institute of Technology (193)
- University of Arkansas Little Rock (154)
-
- University of South Carolina (127)
- Virginia Commonwealth University (112)
- University of Texas Rio Grande Valley (76)
- Columbus State University (60)
- Mississippi State University (60)
- Rowan University (46)
- City University of New York (CUNY) (14)
- Illinois State University (14)
- American University in Cairo (13)
- University of North Dakota (3)
- Nova Southeastern University (2)
- St. John's University (2)
- Texas A&M International University (2)
- Pepperdine University (1)
- SASTRA Deemed to be University (1)
- Keyword
-
- Machine learning (128)
- #antcenter (63)
- Deep learning (50)
- Software engineering (50)
- Computer networks--Security measures (47)
-
- Machine Learning (47)
- Artificial intelligence (46)
- Computer security (44)
- Cybersecurity (33)
- Security (29)
- Computer vision (28)
- Object-oriented programming (Computer science) (27)
- Simulation (25)
- Virtual reality (25)
- Algorithms (24)
- Deep Learning (24)
- Neural networks (Computer science) (24)
- Computer (23)
- Artificial Intelligence (21)
- Image processing (21)
- Computer simulation (20)
- Expert systems (Computer science) (20)
- Genetic algorithms (20)
- Intelligent agents (Computer software) (19)
- Neural networks (19)
- Applied sciences (18)
- Natural Language Processing (18)
- Natural language processing (18)
- Computer graphics (17)
- Optimization (17)
- Publication Year
- File Type
Articles 91 - 120 of 2733
Full-Text Articles in Computer Sciences
Zeroizing Trust In A Naïve Federated Zero Trust Environment, Keith E. Strandell
Zeroizing Trust In A Naïve Federated Zero Trust Environment, Keith E. Strandell
Theses and Dissertations
The position of the United States on the global stage is predicated on information dominance and the ability to project power through cooperative engagements with mission partners in both wartime and peacetime. Recent cyber-attacks highlighted the need for a more robust cybersecurity posture. As the United States progresses toward the adoption of Zero Trust, it is incumbent on the Department of Defense to assess the impact to the ability to share data across strategic partnerships while securing the data of both the United States and its partners. This paper proposes research into ensuring an environment rooted in Zero Trust and …
Promoting Collaboration And Multi-Directional Reliance By Sharing Mental Model Information For Effective Multi-Agent Teaming, Audrey L. Aldridge
Promoting Collaboration And Multi-Directional Reliance By Sharing Mental Model Information For Effective Multi-Agent Teaming, Audrey L. Aldridge
Theses and Dissertations
Successful human-agent teaming requires teammates to form and maintain a shared or common understanding of several attributes regarding taskwork and teamwork. With enhanced information sharing, mental model development, and team functionality, teammates (human, autonomous) can learn to anticipate each others' behaviors, preferences, and needs as well as understand their capabilities and limitations. In designing a framework to support this type of cooperative teaming, there is a need to determine how sharing knowledge, mental models, and common understandings impacts teaming dynamics and performance. By incorporating each individual's understanding into a human-agent interface, this research enables better team coordination and performance through …
A Framework For Modular Knowledge Composition In Network Intrusion Detection Systems, Patrick L. Day
A Framework For Modular Knowledge Composition In Network Intrusion Detection Systems, Patrick L. Day
Theses and Dissertations
Autonomic Intrusion Detection Systems (AIDS) are sophisticated software systems designed to autonomously and adaptively identify and respond to security threats and intrusions in computer networks or systems. One of the fundamental challenges in intrusion detection research lies in the limited availability and scope of publicly available datasets. The proposed research aims to address data-related gaps with autonomic and traditional intrusion detection systems by describing a comprehensive approach to investigate the impact and potential of data augmentation. The goal is to explore various data augmentation techniques, assess their effectiveness in introducing variability, and evaluate their impact on the performance of neural-based …
Optimizing Mars Terrain Segmentation With Weakly Supervised Learning: A Focus On Weighted Loss From Annotation Metadata, Malika Dutta
Optimizing Mars Terrain Segmentation With Weakly Supervised Learning: A Focus On Weighted Loss From Annotation Metadata, Malika Dutta
Theses and Dissertations
The study of planetary surfaces heavily depends upon space rovers that gather detailed images of terrain needed for analysis and navigation. Deep neural networks and other sophisticated machine learning techniques are necessary for autonomous navigation in challenging terrain. However, the inconsistent annotations by citizen scientists frequently hinder the performance of these models. This study seeks to optimize terrain segmentation to improve the autonomous capabilities of future Mars rovers by presenting a novel weakly supervised learning framework to handle noise and unreliability in datasets. Using factors like number of clicks, pixel accuracy, and annotator dependability, the method utilizes annotation metadata in …
Bucket-Based Priority Queues For A* And Related Bounded-Suboptimal And Anytime Search Algorithms: Theoretical And Practical Advancements, Garrett Michael Fereday
Bucket-Based Priority Queues For A* And Related Bounded-Suboptimal And Anytime Search Algorithms: Theoretical And Practical Advancements, Garrett Michael Fereday
Theses and Dissertations
For shortest-path problems with a small number of integer transition costs, it is well-known that the performance of the classic A* algorithm can be improved by using bucketing to reduce priority queue overhead—in particular, by using a bucket queue data structure for the priority queue, instead of a binary heap. This dissertation describes several theoretical and practical extensions of this approach. First, the traditional two-level bucket queue data structure is modified in simple ways to improve the worst-case complexity of its operations, which leads to the first demonstration that the priority queue operations of a two-level bucket queue for A* …
Establishing A Baseline For Detecting Lotl Attacks In Windows Operating Systems, Ashlyn Martin Phillips
Establishing A Baseline For Detecting Lotl Attacks In Windows Operating Systems, Ashlyn Martin Phillips
Theses and Dissertations
There has been an increasing realization of the rise in living off the land (LOTL) attacks where adversaries misuse legitimate system tools, particularly with state-sponsored actors targeting critical infrastructure in the United States. These attacks are difficult to detect because they allow attackers to remain present in a system without the user’s knowledge for an extended period. This thesis establishes an initial baseline specifically for Windows operating systems to measure normal system activity, focusing on CPU usage, memory utilization, and process activity. It particularly examines the use of PowerShell alongside other applications. The findings from this baseline are used to …
Application Of Pu Learning In Detection Of Ddos Attacks, Gagana Sathya Narayana Prasad
Application Of Pu Learning In Detection Of Ddos Attacks, Gagana Sathya Narayana Prasad
Theses and Dissertations
The gcore radar 2024 says, the number of DDoS attacks has been increased by 46% in 12 months. Supervised and unsupervised techniques struggle detecting DDoS attacks due to the scarcity of labeled attack samples and an overwhelming presence of benign traffic. In contrast PU- Learning offers a promising solutions by dividing the data into positive and unlabeled data. This study explores the effectiveness of PU-learning in detecting DDoS attacks by comparing it with unsupervised methods. This method employs PU Bagging, Two Step method and auto-encoder based models to extract meaningful patters from network traffic data, utilizing CICDDoS2017 dataset for evaluation. …
Efficient Eeg Epilepsy Classification And Feature Selections Based On Hellinger Distance, Muhammed Sadiq
Efficient Eeg Epilepsy Classification And Feature Selections Based On Hellinger Distance, Muhammed Sadiq
Theses and Dissertations
Accurate and efficient detection of epileptic seizures from EEG signals remains a critical challenge due to high-dimensional data, class imbalance, and the limitations of standard classifiers. This thesis introduces two novel models to address these challenges. The first model presents a new classifier based on the Hellinger Distance, specifically designed to enhance discriminative capability and robustness against imbalanced datasets. By integrating the Hellinger Distance Classifier with Particle Swarm Optimization (PSO) for feature selection, this model significantly improves classification performance while reducing computational complexity. Experimental evaluations on the Bonn dataset demonstrate an accuracy of 96.25%, an F1-score of 97.74%, a recall …
Applications Of The Mathieu Groups And Information Theory In Dna Encoding Functions, Juan C. Nava Jr
Applications Of The Mathieu Groups And Information Theory In Dna Encoding Functions, Juan C. Nava Jr
Theses and Dissertations
A foundational idea in mathematics lies in breaking down existing components into their bare fundamentals. As evidenced by prime numbers and composites, we learn this idea at an early age. Categorizing these broken-down components into their simplest form allows mathematicians to construct proofs from emergent patterns. John Conway’s Atlas of Finite Groups in the 1990s was particularly concerned with the categorization of structures known as groups. There are certain axioms a group must adhere to, which amount to the retention of symmetry; ultimately a group helps us to better understand symmetric actions performed on a set with a binary operation. …
Modeling Cross-Platform Narrative Templates: A Temporal Knowledge Graph Approach, Ridwan Amure
Modeling Cross-Platform Narrative Templates: A Temporal Knowledge Graph Approach, Ridwan Amure
Theses and Dissertations
Over the past decade, social media platforms have rapidly evolved in scale, functionality, and user engagement, encouraging individuals to maintain active presences across multiple networks. This complex, interconnected ecosystem has also enabled information actors to exploit cross-platform dynamics to amplify the reach of their content and strategically target diverse audiences. Recognizing the persistence and adaptability of such actors, this research emphasizes the need for robust models that can effectively capture and analyze cross-platform narrative diffusion. To this end, we propose a framework that utilizes temporal knowledge graphs to model the evolution and relationships among narratives across platforms. We extract temporal …
The Evolution And Impact Of Blog Analysis Tools: A Study Of Blogtracker's Comprehensive Approach To Digital Discourse Analysis, Oyindamola Koleoso
The Evolution And Impact Of Blog Analysis Tools: A Study Of Blogtracker's Comprehensive Approach To Digital Discourse Analysis, Oyindamola Koleoso
Theses and Dissertations
This study presents BlogTracker, a comprehensive web-based platform designed to address the growing complexities of analyzing the modern blogosphere. We detail BlogTracker's evolution from earlier blog analysis tools, highlighting its innovative integration of features including real-time data collection, advanced content analysis, sentiment analysis, influence tracking, and narrative analysis. At the core of our contribution is a robust content extraction system that achieves 91.33% accuracy across diverse blog formats, providing a reliable foundation for all analytical functions. This extraction system effectively distinguishes between primary content and peripheral elements, ensuring high-quality inputs for downstream analysis regardless of source blog structure. The platform's …
Dynamic Approaches To Missing Data In Healthcare: Evaluating Ensemble Models, Feature Selection, And Meta-Features, Dylan Dominguez Sulca
Dynamic Approaches To Missing Data In Healthcare: Evaluating Ensemble Models, Feature Selection, And Meta-Features, Dylan Dominguez Sulca
Theses and Dissertations
Missing data is pervasive in healthcare, where incomplete observations commonly arise from patient dropout, sensor failures, or privacy constraints. This research presents an investigation into handling such data, focusing on (1) Missingness-Aware Dynamic Ensemble Weighting (MDEW), (2) feature selection under varying missing rates, (3) autoencoder-based imputation (ODAE), and (4) a meta-feature analysis guiding pipeline selection. We evaluate our experiments on four diverse datasets, Cleveland Heart Disease, Diabetic Retinopathy, Breast Cancer Wisconsin, EEG Eye State. Our research shows that MDEW adaptively selects imputer classifier pipelines, outperforming single model and uniform averaging baselines at moderate to high missingness 10% to 50%. Filter …
Unpaired Virtual Histological Staining Of Tissue From Autofluorescence Using Regularized Cycle-Consistent Adversarial Networks, Zhesi Wen
Theses and Dissertations
We present a regularized CycleGAN with a Dense Residual U-Net to virtually stain autofluorescence images of tissue into H&E-like images. Our method outperforms standard architectures, reduces artifacts, and achieves superior FID scores, enabling efficient, label-free, and accurate digital pathology for unpaired datasets using multi-channel fluorescence inputs.
Intuiting Interaction: Meta-Reasoning And Meta-Learning As Foundations For Intelligent User Interfaces, Jeffrey Hsu
Intuiting Interaction: Meta-Reasoning And Meta-Learning As Foundations For Intelligent User Interfaces, Jeffrey Hsu
Theses and Dissertations
This research presents MARCO—a cognitive framework for Intelligent User Interfaces that uses meta-reasoning for context-aware adaptation across diverse tasks. It integrates multiple reasoning modules coordinated by a Meta-Cognitive Unit that selects strategies based on evolving demands. Evaluations show MARCO outperforms baselines in reasoning accuracy and computational efficiency.
Optimizing Small Ai Models For Biomedical Tasks Through Efficient Knowledge Transfer From Large Domain Models, Girish Sundaram
Optimizing Small Ai Models For Biomedical Tasks Through Efficient Knowledge Transfer From Large Domain Models, Girish Sundaram
Theses and Dissertations
The PICO (Population, Intervention, Comparison, Outcome) framework is a widely adopted methodology for structuring clinical research questions and extracting relevant information from unstructured medical texts. However, traditional approaches for PICO classification demand computationally expensive domain-specific language models, such as BioBERT and ClinicalBERT, which require extensive training and large annotated datasets. This dissertation introduces Distilled Rapid Embedding Transfer (DRET), a novel knowledge transfer method designed to enable resource-constrained domain adaptation. DRET aims to efficiently transfer biomedical domain knowledge from large, specialized models to a compact, general-purpose model, DistilBERT, thereby enhancing its ability to perform domain-specific tasks without access to the original …
Cross-Dataset Fairness Evaluation Of Transformer-Based Sentiment Models, Sara Zuiran
Cross-Dataset Fairness Evaluation Of Transformer-Based Sentiment Models, Sara Zuiran
Theses and Dissertations
With the growing exploration of Natural Language Processing (NLP) systems in decision-making environments, it is essential to evaluate technical and ethical aspects of the dataset and the NLP model to improve fairness. To assess fairness, the thesis examines demographic imbalances in sentiment classification models by evaluating transformer-based models fine-tuned on the Stanford Sentiment Treebank version 2 dataset (SST-2) against the demographically annotated Comprehensive Assessment of Language Model dataset (CALM). This work identifies performance disparities in sentiment prediction across demographic groups by examining sensitive attributes such as gender and race. The study evaluates both the RoBERTa and MentalBERT transformer models using …
Bridging The Gap: Enhancing Devops Security Through Comprehensive Threat Modeling, Ashutosh Jagdish Sonar
Bridging The Gap: Enhancing Devops Security Through Comprehensive Threat Modeling, Ashutosh Jagdish Sonar
Theses and Dissertations
Today, security is an essential component of software development, especially in DevOps environments where rapid and continuous product release cycles are common. Systems are vulnerable to new attacks because traditional security approaches often cannot keep up with the pace of change. The threat modeling approaches used in DevOps are examined in this thesis, along with their advantages, disadvantages, and suitability for use in current software development processes. Well-known frameworks including STRIDE (Spoofing, Tampering, Repudiation, Information Disclosure, Denial of Service (DoS), and Elevation of Privilege), Attack Trees, LINDDUN (Linking, Identifying, Non-Repudiation, Detecting, Data Disclosure, Unawareness, and Non-Compliance.), Practical Threat Analysis (PTA), …
Personality Trait Recognition Through Deep Neural Temporal Modeling Of Non-Verbal Behavior, Kushal Vangara
Personality Trait Recognition Through Deep Neural Temporal Modeling Of Non-Verbal Behavior, Kushal Vangara
Theses and Dissertations
Personality research seeks to explain the wide range of human behaviors through stable, measurable traits. Human interactions are inherently rich and multidimensional, and analyzing behavioral data offers a promising path to uncover personality insights. The increasing convergence of psychology, computer science, and machine learning has fueled interest in computational approaches to personality assessment. Advances in sensing technologies have made it possible to capture fine-grained information about individuals’ behaviors and interactions in naturalistic and controlled environments. Automated audio-visual analysis techniques extract relevant behavioral cues, which machine learning models then interpret to infer underlying personality traits. This work provides a comprehensive overview …
Early Breast Cancer Detection With Ultrasound Data Using Nmf, Rutvi Khamar
Early Breast Cancer Detection With Ultrasound Data Using Nmf, Rutvi Khamar
Theses and Dissertations
Early detection of breast cancer significantly influences patient outcomes. Dynamic Contrast-Enhanced Ultrasound (DCE-US) has shown promise in early detection by visualizing tumor vascularity and perfusion dynamics in real-time. This study evaluates the efficacy of DCE-US in distinguishing four stages of cancer progression: normal, hyperplasia, ductal carcinoma in situ (DCIS), and invasive cancer, using a transgenic mouse model that mimics human breast cancer. Ultrasound burst pulses, while commonly used to remove unbound contrast agents, can potentially damage human tissues. Using the pre-pulse data helps mitigate this risk, ensuring safer and more reliable measurements. A VEGFR2-targeted microbubble contrast agent was injected, and …
Improving Home Security Through User Centered Device Positioning, Lalith Nadipalli
Improving Home Security Through User Centered Device Positioning, Lalith Nadipalli
Theses and Dissertations
In today’s world, where technology is advancing rapidly and security threats are becoming more complex, the need for effective home safety measures is more critical than ever. Homeowners are increasingly turning to a variety of smart devices, such as smoke detectors, carbon monoxide detectors, and security cameras, to protect their living spaces against potential dangers like burglary, fire, and environmental hazards. These devices offer essential protection, acting as both early warning systems and visual surveillance tools. However, their effectiveness largely hinges on how well they are placed within the home. Proper placement of these safety devices ensures that they provide …
Effects Of Reflective Journaling And Nudges On Academic Motivation And Engagement, Lakshmi Satya Sai Veda Mahita Uppuluri
Effects Of Reflective Journaling And Nudges On Academic Motivation And Engagement, Lakshmi Satya Sai Veda Mahita Uppuluri
Theses and Dissertations
This study investigates the effects of reflective journaling and motivational nudges on academic motivation and engagement among college students. Grounded in Self- Determination Theory (SDT), the research examines how different interventions influence intrinsic motivation, and academic behaviors such as class attendance, participation, and preparation. The study employed a between-group experimental design with three conditions: a control group, a journaling group, and a journaling group that also received daily motivational nudges. Results showed that students in the journaling groups—particularly those who received nudges—experienced a significant increase in academic motivation. While changes in academic engagement were not significant, the effect size suggested …
Expressive And Interpretable User Engagement Prediction Using Multivariate Survival Processes, Akshay Aravamudan
Expressive And Interpretable User Engagement Prediction Using Multivariate Survival Processes, Akshay Aravamudan
Theses and Dissertations
The ability to characterize how information diffuses online is of paramount importance to stakeholders that are interested in tasks such as proposing solutions for mitigating and countering dis/misinformation, predicting user engagement of content in social media, planning marketing campaigns to roll-out products and planning dissemination of political campaign messaging among others. One such facet of learning the dynamics of information diffusion is the ability to predict user engagement or the popularity of a single piece of information as it spreads through an online medium. Existing works in this regard mainly either obfuscate user level information or utilize frameworks that are …
Advancing Precision And Autonomy In Agriculture And Medical Imaging Through Ai And Computer Visions, Tan-Hanh Pham
Advancing Precision And Autonomy In Agriculture And Medical Imaging Through Ai And Computer Visions, Tan-Hanh Pham
Theses and Dissertations
Deep learning has revolutionized numerous fields by enhancing precision, automation, and decision-making capabilities. This dissertation explores its applications in agriculture and medical image processing, introducing novel methodologies to improve accuracy and efficiency in these domains. These fields hold critical societal importance -- agriculture underpins global food security and sustainability, while medical imaging drives advancements in diagnostics and personalized healthcare, both benefiting significantly from data-driven innovations. In agriculture, deep learning is applied to precision spray systems through droplet analysis. Specifically, a generative model is designed to create synthetic droplet images, addressing the challenge of limited training samples, which are expensive …
Generalizable Skill Learning In Robotic Agents Using Transformer Models, Erik Enriquez
Generalizable Skill Learning In Robotic Agents Using Transformer Models, Erik Enriquez
Theses and Dissertations
This work explores the application of Transformer models to robotic skill learning, aiming to enhance generalization across various physical tasks and environments with continuous control. Despite their success in other domains, our experiments reveal that the utility of Transformers in robotics heavily depends on pretraining strategies. Specifically, Transformers pretrained on reinforcement learning tasks generalized effectively, while those trained with task-agnostic masking strategies did not. These findings challenge assumptions about the universality of Transformer-based methods and underscore the importance of domain-aligned pretraining for developing versatile robotic agents.
Towards Visual Inertial Navigation With Fixed Tetrahedral Targets, Joao Leonardo Silva Cotta
Towards Visual Inertial Navigation With Fixed Tetrahedral Targets, Joao Leonardo Silva Cotta
Theses and Dissertations
This dissertation presents a robust method for 6DoF position estimation under impaired visual conditions utilizing a minimum 4-point Perspective-n-Point (P4P) solver designed for tetrahedral targets. Using SO(3) × R 3 instead of SE(3), the method uses a Lie group-based formulation to discriminate between rotation and translation, thereby enabling computationally efficient, resource-conscious op- optimization while preserving correct geometric behavior. Designed using the contemporary C++17 library ShomerTarget, the solver is analytically formulated and assessed under pragmatic robotic conditions. Particularly in low-light and high-dynamic environments, experiments on embedded systems, UAVs, and NASA’s Astrobee show that the proposed solver attains enhanced accuracy compared to …
Fairness And Robustness In Decentralized Federated Learning, Kaichuang Zhang
Fairness And Robustness In Decentralized Federated Learning, Kaichuang Zhang
Theses and Dissertations
Federated Learning (FL) has emerged as a privacy-preserving paradigm that allows multiple clients to collaboratively train a machine learning model without sharing raw data. However, traditional FL relies on a central server for model aggregation, which introduces a single point of failure and makes the system vulnerable to server-side attacks or breakdowns. To address these limitations, Decentralized Federated Learning (DFL) has been proposed, eliminating the need for a central server and enhancing system resilience. Despite these advantages, DFL faces critical challenges related to fairness and robustness, especially under non-i.i.d. data distributions and adversarial conditions. In this thesis, we propose a …
An Analysis Of Face Morphing Presentation Attacks Against Facial Recognition Systems, Joshua Breininger
An Analysis Of Face Morphing Presentation Attacks Against Facial Recognition Systems, Joshua Breininger
Theses and Dissertations
Security has been a problem for human society for as long as history has been recorded. The identification of people is an ongoing, ancient battle, with a variety of methods that only become more complex with time. The Romans performed censuses, ciphers have been used for thousands of years in the pursuit of security, and in modern day we own identifications and governments keep track of who lives in their country with citizenship and licenses. The question of ”Who are you?” is vital for society to function, which opens up a massive field of potential for how to ask that …
Building Trustable Methods For Group Recommendations: Advancing Fairness And Robustness Across Domains, Siva Likitha Valluru
Building Trustable Methods For Group Recommendations: Advancing Fairness And Robustness Across Domains, Siva Likitha Valluru
Theses and Dissertations
On the internet, where the number of available choices for information is exponentially growing, there is a need to prioritize and deliver relevant results to users efficiently, on demand. Recommendation systems (RSs) address that need by searching through and filtering large amounts of dynamically generated information and providing users with recommendations tailored to them. These systems have primarily focused on (1) single-user models, where recommendations are tailored towards a specific individual, or (2) single-item models, where items are recommended based on a broader appeal to users and similarities in item metadata, in the past. In many real-world scenarios, however, recommendation …
Neural Network-Based Low-Level 3d Point Cloud Processing, Pingping Cai
Neural Network-Based Low-Level 3d Point Cloud Processing, Pingping Cai
Theses and Dissertations
3D computer vision is a promising research field with the potential to revolutionize future lifestyles. Among various 3D representation formats, point clouds stand out for their efficiency in depicting 3D objects using a set of coordinates, enabling advancements in fields such as autonomous driving, virtual reality, and robotics. Due to the limitations of sensor fields of view and scanning trajectories, the collected point clouds are usually sparse, noisy, and incomplete, impeding the performance of many downstream applications. Thus, the tasks of low-level point cloud processing are proposed to refine and generate dense, clean, and complete point clouds. To accomplish these …
Hallucinations In Large Foundation Models: Characterization, Quantification, Detection, Avoidance, And Mitigation, Vipula Rawte
Hallucinations In Large Foundation Models: Characterization, Quantification, Detection, Avoidance, And Mitigation, Vipula Rawte
Theses and Dissertations
Deception is an inherent aspect of social interactions, with research indicating that most people engage in deceptive behavior at least once or twice daily . In parallel, advances in artificial intelligence have led to machines exhibiting deceptive tendencies. These deceptions can be categorized into two types: unintended and intentional. Unintended deceptions - often referred to as hallucinations - occur when generative AI systems produce plausible and convincing narratives yet are factually inaccurate. This phenomenon primarily results from the systems' architectural design, extensive parametric memory, and reliance on statistical assumptions. In this thesis, we provide a comprehensive discussion on the characterization, …