Artificial Intelligence and Robotics Commons^™

Ocr Post-Processing Using Large Language Models, Mahdi Hajiali

UNLV Theses, Dissertations, Professional Papers, and Capstones

Optical Character Recognition (OCR) technology transforms textual visuals into an electronically readable, non-graphical format of the text. This allows the editing and other text manipulation of the content by language technology software such as machine translation, text comprehension, query-answering systems, and search engines. While Optical Character Recognition (OCR) systems continually progress towards greater precision, several complications persist when dealing with low-resolution source images or those with multicolored backgrounds. Consequently, the text derived from OCR necessitates additional refinement to optimize accuracy, beneficial for various subsequent applications. It is recognized that the character accuracy of OCR-generated text may influence certain natural language …

A Multi-Layer Information Dissemination Model And Interference Optimization Strategy For Communication Networks In Disaster Areas, Yuexia Zhang, Yang Hong, Mohsen Guizani, Sheng Wu, Peiying Zhang, Ruiqi Liu

Machine Learning Faculty Publications

The communication network in disaster areas (CNDA) can disseminate the key disaster information in time and provide basic information support for decision-making and rescuing. Therefore, it is of great significance to study the information dissemination mechanism of CNDA. However, a CNDA is vulnerable to interference, which affects information dissemination and rescuing. To solve this problem, this paper established a multi-layer information dissemination model of CNDA (MMND) which models the CNDA from the perspective of degree distribution of nodes. The information dissemination process and equilibrium state in CNDA is analyzed by an improved dynamic dissemination method. Then, the effects of the …

Self-Supervised Pretraining And Transfer Learning On Fmri Data With Transformers, Sean Paulsen

Dartmouth College Ph.D Dissertations

Transfer learning is a machine learning technique founded on the idea that knowledge acquired by a model during “pretraining” on a source task can be transferred to the learning of a target task. Successful transfer learning can result in improved performance, faster convergence, and reduced demand for data. This technique is particularly desirable for the task of brain decoding in the domain of functional magnetic resonance imaging (fMRI), wherein even the most modern machine learning methods can struggle to decode labelled features of brain images. This challenge is due to the highly complex underlying signal, physical and neurological differences between …

Autonomous Shipwreck Detection & Mapping, William Ard

LSU Master's Theses

This thesis presents the development and testing of Bruce, a low-cost hybrid Remote Operated Vehicle (ROV) / Autonomous Underwater Vehicle (AUV) system for the optical survey of marine archaeological sites, as well as a novel sonar image augmentation strategy for semantic segmentation of shipwrecks. This approach takes side-scan sonar and bathymetry data collected using an EdgeTech 2205 AUV sensor integrated with an Harris Iver3, and generates augmented image data to be used for the semantic segmentation of shipwrecks. It is shown that, due to the feature enhancement capabilities of the proposed shipwreck detection strategy, correctly identified areas have a 15% …

Vertical Federated Learning Using Autoencoders With Applications In Electrocardiograms, Wesley William Chorney

Theses and Dissertations

Federated learning is a framework in machine learning that allows for training a model while maintaining data privacy. Moreover, it allows clients with their own data to collaborate in order to build a stronger, shared model. Federated learning is of particular interest to healthcare data, since it is of the utmost importance to respect patient privacy while still building useful diagnostic tools. However, healthcare data can be complicated — data format might differ across providers, leading to unexpected inputs and incompatibility between different providers. For example, electrocardiograms might differ in sampling rate or number of leads used, meaning that a …

Ide-Based Learning Analytics For Assessing Introductory Programming Skill, Phyllis J. Beck

Theses and Dissertations

Providing a sufficient level of personalized feedback on students' current level of strategic knowledge within the context of the natural programming environment through IDE-based learning analytics would transform learning outcomes for introductory programming students. However, providing sufficient insight into the programming process was previously inaccessible due to the need for more complex and scalable data collection methods and metrics with a wider variety for understanding programming metacognition and the full programming process.

This research developed a custom-built web-based IDE and event compression system to investigate two of the five components of a five-dimensional model of cognition for programming skill estimation …

Proposing A Measure Of Ethicality For Humans And Ai, Alejandro Jorge Napolitano Jawerbaum

Electronic Theses and Dissertations

Smarter people or intelligent machines are able to make more accurate inferences about their environment and other agents more efficiently than less intelligent agents. Formally: ‘Intelligence measures an agent’s ability to achieve goals in a wide range of environments.’ (Legg, 2008)

In this dissertation we extend this definition to include ethical behaviour and we will offer a mathematical formalism and a way to estimate how ethical an action is or will be, both for a human and for a computer, by calculating the expected values of random variables. Formally, we propose the following measure of ethicality, which is computable, or …

Arabic Dysarthric Speech Recognition Using Adversarial And Signal-Based Augmentation, Massa Baali, Ibrahim Almakky, Shady Shehata, Fakhri Karray

Machine Learning Faculty Publications

Despite major advancements in Automatic Speech Recognition (ASR), the state-of-the-art ASR systems struggle to deal with impaired speech even with high-resource languages. In Arabic, this challenge gets amplified, with added complexities in collecting data from dysarthric speakers. In this paper, we aim to improve the performance of Arabic dysarthric automatic speech recognition through a multi-stage augmentation approach. To this effect, we first propose a signal-based approach to generate dysarthric Arabic speech from healthy Arabic speech by modifying its speed and tempo. We also propose a second stage Parallel Wave Generative (PWG) adversarial model that is trained on an English dysarthric …

S2cd: Self-Heuristic Speaker Content Disentanglement For Any-To-Any Voice Conversion, Pengfei Wei, Xiang Yin, Chunfeng Wang, Zhonghao Li, Xinghua Qu, Zhiqiang Xu, Zejun Ma

Machine Learning Faculty Publications

In this paper, we propose a Self-heuristic Speaker Content Disentanglement (S2CD) model for any to any voice conversion without using any external resources, e.g., speaker labels or vectors, linguistic models, and transcriptions. S2CD is built on the disentanglement sequential variational autoencoder (DSVAE), but improves DSVAE structure at the model architecture level from three perspectives. Specifically, we develop different structures for speaker and content encoders based on their underlying static/dynamic property. We further propose a generative graph, modelled by S2CD, so as to make S2CD well mimic the multi-speaker speech generation process. Finally, we propose a self-heuristic way to introduce bias …

Fooctts: Generating Arabic Speech With Acoustic Environment For Football Commentator, Massa Baali, Ahmed Ali

Machine Learning Faculty Publications

This paper presents FOOCTTS, an automatic pipeline for a football commentator that generates speech with background crowd noise. The application gets the text from the user, applies text pre-processing such as vowelization, followed by the commentator's speech synthesizer. Our pipeline included Arabic automatic speech recognition for data labeling, CTC segmentation, transcription vowelization to match speech, and fine-tuning the TTS. Our system is capable of generating speech with its acoustic environment within limited 15 minutes of football commentator recording. Our prototype is generalizable and can be easily applied to different domains and languages.

Controllable Language Generation Using Deep Learning, Rohola Zandie

Electronic Theses and Dissertations

The advent of deep neural networks has sparked a revolution in Artificial Intelligence (AI), notably with the creation of Transformer models like GPT-X and ChatGPT. These models have surpassed previous methods in various Natural Language Processing (NLP) tasks. As the NLP field evolves, there is a need to further understand and question the capabilities of these models. Text generation, a crucial part of NLP, remains an area where our comprehension is limited while being critical in research.

This dissertation focuses on the challenging problem of controlling the general behaviors of language models such as sentiment, topical focus, and logical reasoning. …

Terrain And Adversary-Aware Autonomous Robot Navigation, Aniekan Ufot Inyang

Electronic Theses and Dissertations

In autonomous robot navigation, the robot is able to understand the environment around it for intelligent navigation. From its world model of this environment, it generates a global plan for navigation from a position to a goal based on different factors. This research aims to implement autonomous robot navigation by learning terrain affordances: traversability (moving quickly) and concealment (staying hidden from an adversary) using the Preference-based Inverse Reward Learning (PbIRL) methodology. The PbIRL methodology reduces the barrier of generating initial demonstration data to learn the terrain affordances by using a human expert’s preferences to learn individual weights over the terrain …

Topology Optimization For Artificial Neural Networks, Justin Mills

Masters Theses & Specialist Projects

This thesis examines the feasibility of implementing two simple optimization methods, namely the Weights Power method (Hagiwara, 1994) and the Tabu Search method (Gupta & Raza, 2020), within an existing framework. The study centers around the generation of artificial neural networks using these methods, assessing their performance in terms of both accuracy and the capacity to reduce components within the Artificial Neural Network’s (ANN) topology.

The evaluation is conducted on three classification datasets: Air Quality (Shahane, 2021), Diabetes (Soni, 2021), and MNIST (Deng, 2012). The main performance metric used is accuracy, which measures the network's predictive capability for the classification …

Evaluating Chatgpt For Recommendation: How Does The Ability To Converse Impact Recommendation?, Kyle Spurlock

Electronic Theses and Dissertations

Recommendation algorithms have become an absolute necessity in the modern world to avoid information overload. However, the interaction between the human and the system is largely superficial and without any real contact. If you are given poor recommendations, you have no choice but to sift through mountains of content on your own until the model learns to accommodate your tastes more. This is bad for business as well as the consumer. Recently, large language models like ChatGPT have seen a significant rise in popularity due to their ease of use and wide range of knowledge. It has now become nearly …

Application Of Machine Learning Algorithms For Elucidation Of Biological Networks From Time Series Gene Expression Data, Krupa Nagori

Computational and Data Sciences (PhD) Dissertations

This dissertation provides a deep dive into understanding gene expression, interaction, regulation, and the intricate mechanisms behind heliotropism and phototropism. Additionally, the research accentuates the significance of machine learning techniques, specifically for gene regulatory networks (GRNs).

Chapter 1 offers an exhaustive benchmarking of GRN methodologies, furthering our comprehension of machine-learning models relevant to GRNs. The evaluation revealed that GRNTE, SWING, and BiXGBoost emerged as top-performing methods in GRN inference. The suitability of these models varies depending on specific research criteria such as computational needs, dataset dimensions, and performance metric emphasis. An innovation of this chapter was the introduction of Colab …

Generalizable Deep-Learning-Based Wireless Indoor Localization, Ali Owfi

All Theses

The growing interest in indoor localization has been driven by its wide range of applications in areas such as smart homes, industrial automation, and healthcare. With the increasing reliance on wireless devices for location-based services, accurate estimation of device positions within indoor environments has become crucial. Deep learning approaches have shown promise in leveraging wireless parameters like Channel State Information (CSI) and Received Signal Strength Indicator (RSSI) to achieve precise localization. However, despite their success in achieving high accuracy, these deep learning models suffer from limited generalizability, making them unsuitable for deployment in new or dynamic environments without retraining. To …

Seek And Classify: End-To-End Joint Multi-Signal Detection And Classification Using Deep Learning, Prashant Subedi

School of Computing: Dissertations, Theses, and Student Research

The rise in the use of wireless communication has led to the problem of spectrum scarcity in licensed bands. The popularity of Internet of Things (IoT) requires innovative solutions that maximize the use of available spectrum to support the increasing number of connected devices. This thesis tackles two significant problems in wireless communication: the need for efficient spectrum sensing techniques and the scarcity of large, diverse raw in-phase (I) and quadrature (Q) datasets.

The ability to detect and classify modulation of the signals efficiently can enable a cognitive radio to monitor the spectrum activity in real time and utilize unused …

Mastering Stock Markets With Efficient Mixture Of Diversified Trading Experts, Shuo Sun, Xinrun Wang, Wanqi Xue, Xiaoxuan Lou, Bo An

Research Collection School Of Computing and Information Systems

Quantitative stock investment is a fundamental financial task that highly relies on accurate prediction of market status and profitable investment decision making. Despite recent advances in deep learning (DL) have shown stellar performance on capturing trading opportunities in the stochastic stock market, the performance of existing DL methods is unstable with sensitivity to network initialization and hyperparameter selection. One major limitation of existing works is that investment decisions are made based on one individual neural network predictor with high uncertainty, which is inconsistent with the workflow in real-world trading firms. To tackle this limitation, we propose AlphaMix, a novel three-stage …

Decoding The Underlying Meaning Of Multimodal Hateful Memes, Ming Shan Hee, Wen Haw Chong, Roy Ka-Wei Lee

Research Collection School Of Computing and Information Systems

Recent studies have proposed models that yielded promising performance for the hateful meme classification task. Nevertheless, these proposed models do not generate interpretable explanations that uncover the underlying meaning and support the classification output. A major reason for the lack of explainable hateful meme methods is the absence of a hateful meme dataset that contains ground truth explanations for benchmarking or training. Intuitively, having such explanations can educate and assist content moderators in interpreting and removing flagged hateful memes. This paper address this research gap by introducing Hateful meme with Reasons Dataset (HatReD), which is a new multimodal hateful meme …

Transferable Curricula Through Difficulty Conditioned Generators, Sidney Tio, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Advancements in reinforcement learning (RL) have demonstrated superhuman performance in complex tasks such as Starcraft, Go, Chess etc. However, knowledge transfer from Artificial "Experts" to humans remain a significant challenge. A promising avenue for such transfer would be the use of curricula. Recent methods in curricula generation focuses on training RL agents efficiently, yet such methods rely on surrogate measures to track student progress, and are not suited for training robots in the real world (or more ambitiously humans). In this paper, we introduce a method named Parameterized Environment Response Model (PERM) that shows promising results in training RL agents …

Generalization Through Diversity: Improving Unsupervised Environment Design, Wenjun Li, Pradeep Varakantham, Dexun Li

Research Collection School Of Computing and Information Systems

Agent decision making using Reinforcement Learning (RL) heavily relies on either a model or simulator of the environment (e.g., moving in an 8x8 maze with three rooms, playing Chess on an 8x8 board). Due to this dependence, small changes in the environment (e.g., positions of obstacles in the maze, size of the board) can severely affect the effectiveness of the policy learned by the agent. To that end, existing work has proposed training RL agents on an adaptive curriculum of environments (generated automatically) to improve performance on out-of-distribution (OOD) test scenarios. Specifically, existing research has employed the potential for the …

Learning To Send Reinforcements: Coordinating Multi-Agent Dynamic Police Patrol Dispatching And Rescheduling Via Reinforcement Learning, Waldy Joe, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

We address the problem of coordinating multiple agents in a dynamic police patrol scheduling via a Reinforcement Learning (RL) approach. Our approach utilizes Multi-Agent Value Function Approximation (MAVFA) with a rescheduling heuristic to learn dispatching and rescheduling policies jointly. Often, police operations are divided into multiple sectors for more effective and efficient operations. In a dynamic setting, incidents occur throughout the day across different sectors, disrupting initially-planned patrol schedules. To maximize policing effectiveness, police agents from different sectors cooperate by sending reinforcements to support one another in their incident response and even routine patrol. This poses an interesting research challenge …

Decompiling X86 Deep Neural Network Executables, Zhibo Liu, Yuanyuan Yuan, Shuai Wang, Xiaofei Xie, Lei Ma

Research Collection School Of Computing and Information Systems

Due to their widespread use on heterogeneous hardware devices, deep learning (DL) models are compiled into executables by DL compilers to fully leverage low-level hardware primitives. This approach allows DL computations to be undertaken at low cost across a variety of computing platforms, including CPUs, GPUs, and various hardware accelerators. We present BTD (Bin to DNN), a decompiler for deep neural network (DNN) executables. BTD takes DNN executables and outputs full model specifications, including types of DNN operators, network topology, dimensions, and parameters that are (nearly) identical to those of the input models. BTD delivers a practical framework to process …

Document-Level Relation Extraction Via Separate Relation Representation And Logical Reasoning, Heyan Huang, Changsen Yuan, Qian Liu, Yixin Cao

Research Collection School Of Computing and Information Systems

Document-level relation extraction (RE) extends the identification of entity/mentions’ relation from the single sentence to the long document. It is more realistic and poses new challenges to relation representation and reasoning skills. In this article, we propose a novel model, SRLR, using Separate Relation Representation and Logical Reasoning considering the indirect relation representation and complex reasoning of evidence sentence problems. Specifically, we first expand the judgment of relational facts from the entity-level to the mention-level, highlighting fine-grained information to capture the relation representation for the entity pair. Second, we propose a logical reasoning module to identify evidence sentences and conduct …

Semantically Constitutive Entities In Knowledge Graphs, Chong Cher Chia, Maksim Tkachenko, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Knowledge graphs are repositories of facts about a world. In this work, we seek to distill the set of entities or nodes in a knowledge graph into a specified number of constitutive nodes, whose embeddings would be retained. Intuitively, the remaining accessory nodes could have their original embeddings “forgotten”, and yet reconstitutable from those of the retained constitutive nodes. The constitutive nodes thus represent the semantically constitutive entities, which retain the core semantics of the knowledge graph. We propose a formulation as well as algorithmic solutions to minimize the reconstitution errors. The derived constitutive nodes are validated empirically both in …

Ai For Connectivism Learning: Undergraduate Students’ Experiences Of Chatgpt In Advanced Programming Courses, Swapna Gottipati, Kyong Jin Shim, Venky Shankararaman

Research Collection School Of Computing and Information Systems

Advanced programming skills are required for computing courses on merging topics, and students often struggle to develop these skills to solve complex problems. To address this challenge, faculty members provide additional lectures, practice sessions, and educational technology tools. This paper discusses the challenges faced by computer science students in developing advanced programming skills and explores the use of AI chatbots, specifically ChatGPT, as a support tool for learning. We study the engagement and effectiveness of ChatGPT in helping students learn advanced programming skills using two engagement learning frameworks (CIE and MELT) for evaluation. The study involves designing a computing lab …

Multi-Granularity Detector For Vulnerability Fixes, Truong Giang Nguyen, Cong, Thanh Le, Hong Jin Kang, Ratnadira Widyasari, Chengran Yang, Zhipeng Zhao, Bowen Xu, Jiayuan Zhou, Xin Xia, Ahmed E. Hassan, David Lo, David Lo

Research Collection School Of Computing and Information Systems

With the increasing reliance on Open Source Software, users are exposed to third-party library vulnerabilities. Software Composition Analysis (SCA) tools have been created to alert users of such vulnerabilities. SCA requires the identification of vulnerability-fixing commits. Prior works have proposed methods that can automatically identify such vulnerability-fixing commits. However, identifying such commits is highly challenging, as only a very small minority of commits are vulnerability fixing. Moreover, code changes can be noisy and difficult to analyze. We observe that noise can occur at different levels of detail, making it challenging to detect vulnerability fixes accurately. To address these challenges and …

Numgpt: Improving Numeracy Ability Of Generative Pre-Trained Models, Zhihua Jin, Xin Jiang, Xiangbo Wang, Qun Liu, Yong Wang, Xiaozhe Ren, Huamin Qu

Research Collection School Of Computing and Information Systems

Existing generative pre-trained language models (e.g., GPT) focus on modeling the language structure and semantics of general texts. However, those models do not consider the numerical properties of numbers and cannot perform robustly on numerical reasoning tasks (e.g., math word problems and measurement estimation). In this paper, we propose NumGPT, a generative pre-trained model that explicitly models the numerical properties of numbers in texts. Specifically, it leverages a prototype-based numeral embedding to encode the mantissa of the number and an individual embedding to encode the exponent of the number. A numeral-aware loss function is designed to integrate numerals into the …

Cannabidiol Tweet Miner: A Framework For Identifying Misinformation In Cbd Tweets., Jason Turner

Electronic Theses and Dissertations

As regulations surrounding cannabis continue to develop, the demand for cannabis-based products is on the rise. Despite not producing the psychoactive effects commonly associated with THC, products containing cannabidiol (CBD) have gained immense popularity in recent years as a potential treatment option for a range of conditions, particularly those associated with pain or sleep disorders. However, due to current federal policies, these products have yet to undergo comprehensive safety and efficacy testing. Fortunately, utilizing advanced natural language processing (NLP) techniques, data harvested from social networks have been employed to investigate various social trends within healthcare, such as disease tracking and …

The Development Of Artificial Intelligence-Based To Ols For Expert Peer Review Of Radiotherapy Treatment Plans, Mary Gronberg

Dissertations and Theses (Open Access)

Creating a patient-specific radiation treatment plan is a time-consuming and operator-dependent manual process. The treatment planner adjusts the planning parameters in a trial-and-error fashion in an effort to balance the competing clinical objectives of tumor coverage and normal tissue sparing. Often, a plan is selected because it meets basic organ at risk dose thresholds for severe toxicity; however, it is evident that a plan with a decreased risk of normal tissue complication probability could be achieved. This discrepancy between “acceptable” and “best possible” plan is magnified if either the physician or treatment planner lacks focal expertise in the disease site. …