Engineering Commons^™

Machine Learning For Environmental Sustainability, Syeda Nyma Ferdous

Graduate Theses, Dissertations, and Problem Reports (ETD)

This research proposes a comprehensive approach to address pressing challenges in environmental sustainability, agricultural residue management, using machine learning based approaches. Machine learning (ML) techniques have emerged as powerful tools for addressing environmental sustainability challenges by facilitating the analysis and prediction of ecological phenomena, and optimization of resource management strategies. The study explores the synergies between environmental sustainability and machine learning to develop a framework that leverages artificial intelligence techniques covering a wide range of tasks including crop residue management, soil CO2 flux prediction, and forest carbon system prediction for sustainable development. The study analyze various ML models, such as, …

An Approach For Robotic Pollination That Utilizes Imitation Learning, Ronald Michael Butts Ii

Graduate Theses, Dissertations, and Problem Reports (ETD)

The global decline in pollinator populations poses a significant threat to agriculture, motivating the development of robotic pollination systems. Previous works demonstrated successful robotic pollination of bramble flowers using visual servoing; however, pollination was limited to specific flower orientations. As such, the objective of this work is to develop a robotic pollination system that is capable of pollinating a wider range of orientations.

This research introduces an imitation learning-based framework for robotic pollination that positions the manipulator to view chosen flowers in specific orientations. The developed model leverages object detection (YOLOv8) to identify individual flowers and a convolutional neural network …

Enhancing Robotic Exploration Through Semantically-Guided Sampling Strategies, Christopher Alexander Arend Tatsch

Graduate Theses, Dissertations, and Problem Reports (ETD)

From space and deep-sea exploration to disaster response and environmental monitoring, autonomous robots are essential for advancing science, improving safety, and addressing critical challenges. This dissertation introduces a novel open-source strategy for autonomous robotic exploration: the Semantically-Guided Exploration (SGE) framework. Designed for ground vehicles, SGE integrates semantic understanding into the autonomous exploration process, improving decision-making in complex environments. Specifically, the proposed sampling-based approach uses the information from the semantic segmentation of RGB images and depth images to guide the robot's selection of exploration goals. This method enables the robot to steer away from potential dangers such as large rocks and …

Matthew Gaber: Peekaboo, Matthew Gaber, Mohiuddin Ahmed, Helge Janicke

Research Datasets

Cyber-attacks continue to evolve, increasing in frequency and sophistication where Artificial Intelligence (AI) is becoming essential in detecting modern malware. However, the accuracy of AI in malware detection is dependent on the quality of the features it is trained with. Static and dynamic analysis of malware is limited by the widespread use of obfuscation and anti-analysis techniques employed by malware authors, where if an analysis environment is detected the malware will hide its malicious behavior. However, Dynamic Binary Instrumentation (DBI) allows deep and precise control of the malware sample, thereby facilitating the extraction of authentic features from sophisticated and evasive …

Adaptive Neh With Constrained Nearest Neighbor Subtours For The Electric Vehicle Routing Problem With Time Windows, Andrew Struthers

All Master's Theses

The development of electric vehicles is currently considered one of the most innovative areas in manufacturing. Largely driven by the desire to reduce greenhouse emissions, electric vehicles are seen as a viable alternative to internal combustion engine cars. Starting from consumer cars, a dedicated effort is being made to translate this into commercial vehicles for freight and delivery. This research introduces a novel adaptive Nawaz, Enscore, Ham (NEH) algorithm with constrained nearest neighbor subtour (NEH-NN). This algorithm is tested on the standard benchmark problems in literature and used as a seed solution for the Genetic Algorithm (GA). The performance and …

Applications Of Predictive And Generative Ai Algorithms: Regression Modeling, Customized Large Language Models, And Text-To-Image Generative Diffusion Models, Suhaima Jamal

College of Graduate Studies: Theses & Dissertations

The integration of Machine Learning (ML) and Artificial Intelligence (AI) algorithms has radically changed predictive modeling and classification tasks, enhancing a multitude of domains with unprecedented analytical capabilities. Predictive modeling leverages ML and AI to forecast future trends or behaviors based on historical data, while classification tasks categorize data into distinct classes, from email filtering to medical diagnosis. Concurrently, text-to-image generation has emerged as a transformative potential, allowing visual content creation directly from textual descriptions. These advancements are pivotal in design, art, entertainment, and visual communication, as well as enhancing creativity and productivity. This work explores three significant studies in …

Railroad Condition Monitoring Using Distributed Acoustic Sensing And Deep Learning Techniques, Md Arifur Rahman

College of Graduate Studies: Theses & Dissertations

Proper condition monitoring has been a major issue among railroad administrations since it might cause catastrophic dilemmas that lead to fatalities or damage to the infrastructure. Although various aspects of train safety have been conducted by scholars, in-motion monitoring detection of defect occurrence, cause, and severity is still a big concern. Hence extensive studies are still required to enhance the accuracy of inspection methods for railroad condition monitoring (CM). Distributed acoustic sensing (DAS) has been recognized as a promising method because of its sensing capabilities over long distances and for massive structures. As DAS produces large datasets, algorithms for precise …

Self-Supervised Contrastive Learning Using Eeg Signals For Mental Stress Assessment, Ugochukwu Uraechu

College of Graduate Studies: Theses & Dissertations

A study is presented to investigate self-supervised contrastive learning (SSCL) models using physiological data obtained from non-invasive wearable sensors for mental stress assessment. The present work involved acquisition of electroencephalography (EEG) signals using wearable sensors, signal preprocessing, data augmentation, and investigation of self-supervised contrastive learning (SSCL) algorithms for multi-class mental stress assessment. Seven volunteers participated in this study executing various mental tasks while wearing an OpenBCI head cap to acquire EEG signals. The acquired EEG signals were preprocessed and utilized for data augmentation in time and frequency domains with different SSCL models. Optimal data augmentation combinations and SSCL models were …

On Uncertainty For Ill-Posed Robot Decision Problems, Jared Joseph Beard

Graduate Theses, Dissertations, and Problem Reports (ETD)

As robots adopt more real world responsibilities, they will be expected to solve more complicated problems. In some cases limited prior knowledge will result in unmodelled environmental conditions; in others, multiple users may have competing perspectives on how to frame a decision problem. Many existing frameworks, namely Markov decision processes (MDP) presuppose users have identified a specific problem with models sufficient to solve or learn a problem. If we wish to extend MDPs to novel problems or those heavily dependent on user feedback, autonomous decision makers must be able to identify limitations in how a given problem is framed and …

Designing Ris-Assisted Uav 3d Trajectory Using Deep Reinforcement Learning, Linsong Li

Electronic Theses and Dissertations

Unmanned aerial vehicles (UAVs) are increasingly employed as temporary base stations or access points to facilitate data transfer between ground terminals (GTs). However, in urban environments, UAV-GT communication links often face challenges due to obstructions from buildings and other obstacles, resulting in reduced data transfer efficiency. Reconfigurable intelligent surfaces (RIS) provide a promising solution by reflecting signals to enhance communication quality between UAVs and GTs. This thesis addresses the critical challenge of responsive UAV trajectory optimization in RIS-assisted communication networks. A novel approach is proposed, integrating federated learning with reinforcement learning techniques, specifically Double Deep Q-Network (DDQN) and Deep Deterministic …

Machine Learning For Electronic Structure Prediction, Shashank Pathrudkar

Dissertations, Master's Theses and Master's Reports

Kohn-Sham density functional theory is the work horse of computational material science research. The core of Kohn-Sham density functional theory, the Kohn-Sham equations, output charge density, energy levels and wavefunctions. In principle, the electron density can be used to obtain several other properties of interest including total potential energy of the system, atomic forces, binding energies and electric constants. In this work we present machine learning models designed to bypass the Kohn-Sham equations by directly predicting electron density. Two distinct models were developed: one tailored to predict electron density for quasi one-dimensional materials under strain, while the other is applicable …

Performance Characterization And Optimization Of A Point-Cloud-Based Path Planner In Off-Road Terrains, Casey D. Majhor

Dissertations, Master's Theses and Master's Reports

In this dissertation, I present a multifaceted study on the generation of artificial terrains using a multifractal method, and their use in autonomous ground vehicle (AGV) planning and navigation performance characterization in high-fidelity simulations, and automated parameter optimization.

My first contribution is a multifractal artificial terrain generation method leveraging the 3D Weierstrass-Mandelbrot function to control terrain roughness. We generate 60 unique off-road terrains while varying the fractal dimension and test the impact on vehicle traversal difficulty. Results show that increasing the fractal dimension decreases low-roughness areas, increases semi-rough and high-roughness areas, and decreases vehicle success rates while increasing vertical accelerations, …

Effective Data Augmentation Techniques For Time Series Classification: An Empirical Evaluation, Pongpanod Sankosik

Chulalongkorn University Theses and Dissertations (Chula ETD)

Time series classification is crucial in fields such as healthcare, finance, and industrial processes, but it faces challenges like temporal data ordering, class im-balance, noise, and limited data. This research explores data augmentation techniques to improve classification performance, focusing on the MiniRocket classifier across 85 UCR datasets. The study identifies conditions under which augmentation techniques, like wDBA, enhance accuracy, though overall performance may vary. A dataset-specific approach is essential for effective augmentation. The research also examines the impact of augmentation on datasets with different characteristics, providing insights into when specific strategies are most benefi-cial. Future work includes optimizing augmentation methods …

Sales Forecasting For Retail Business Using Xgboost Algorithm And Timesfm, Prathana Dankorpho

Chulalongkorn University Theses and Dissertations (Chula ETD)

The retail industry is continuously evolving with the expansion of sales channels and the diversification of product assortments. However, current forecasting methods, relying on simplistic statistical models, frequently encounter difficulties in adjusting to the dynamic environment. This limitation leads to challenges in accurately predicting sales. Consequently, there is a critical need to improve the accuracy and frequency of sales predictions to enable timely decision-making for business strategies. Through a comprehensive analysis of datasets from 2019 to 2023, this study illustrates the advantages of integrating XGBoost and TimesFM to gain deeper insights into sales patterns. Results demonstrate a significant enhancement in …

Anonymous Attribute-Based Broadcast Encryption With Hidden Multiple Access Structures, Tran Viet Xuan Phuong

School of Cybersecurity Faculty Publications

Due to the high demands of data communication, the broadcasting system streams the data daily. This service not only sends out the message to the correct participant but also respects the security of the identity user. In addition, when delivered, all the information must be protected for the party who employs the broadcasting service. Currently, Attribute-Based Broadcast Encryption (ABBE) is useful to apply for the broadcasting service. (ABBE) is a combination of Attribute-Based Encryption (ABE) and Broadcast Encryption (BE), which allows a broadcaster (or encrypter) to broadcast an encrypted message, including a predefined user set and specified access policy to …

Observability-Aware Path Planning For Autonomous Navigation, Raymond Brink Neistat

Open Access Master's Theses

Terrain-Aided Navigation (TAN) is a popular method of localization for GPS-denied vehicles, particularly in the marine domain. There are many ways to perform TAN in a marine setting, such as Bathymetric SLAM (BSLAM) and Bayesian Filtering with the aid of an a priori map. These techniques have been studied extensively, but show an overall lack of rigorous observability analyses. Without nonlinear observability analyses, TAN practitioners do not have an analytical indicator to know which areas of terrain will provide opportunities for the best localization performance. This thesis reviews current developments in the endeavors of nonlinear observability analyses as well as …

Deep-Learning Approaches To Predict Remaining Useful Life Of Hard Disks, Rohan Mohapatra

Master's Projects

On a daily basis, data centers process huge volumes of data using inexpensive hard disks. Data stored in these disks serve a range of critical functional needs from financial, and healthcare to aerospace. As such, premature disk failure and consequent loss of data can be catastrophic. To mitigate the risk of failures, cloud storage providers perform condition-based monitoring and replace hard disks before they fail. By estimating the remaining useful life (RUL) of hard disk drives, one can predict the time-to-failure of a particular device and replace it at the right time, ensuring maximum utilization whilst reducing operational costs. We …

Zookeeper Through The Ages: A Comparative Performance Analysis Of Evolutionary Versions, Ashish Khanchandani

Master's Projects

The rise in the need for scalable, fault-tolerant, and high-performance systems is the primary factor driving the developments in distributed computing. However, the proliferation of distributed computing creates significant difficulties. In an internet- scale setting where errors and network delays are frequent, coordinating distributed applications presents difficulties that ZooKeeper attempts to solve. It ensures several crucial characteristics that guarantee reliability and consistency. However, performance and latency play a huge part when it comes to dealing with systems built for handling very high loads. ZooKeeper has very low latency for read-heavy workloads, making it suitable for real-time applications. These factors contribute …

Integrating Chatgpt With A-Frame For User-Driven 3d Modeling, Ivan Hernandez

Master's Projects

ChatGPT is a large language model that is capable of creating conversational text and functional code that can be integrated into various technologies, including computer graphics software. Currently, 3D modeling applications can be relatively difficult for novices to learn and understand due to the overwhelming amount of graphical user interfaces. However, we can remedy this issue by leveraging ChatGPT’s conversational language capabilities. Our project described in this report integrates ChatGPT with A-Frame, an online framework for developing virtual reality experiences, to create an immersive and user-friendly 3D modeling environment where users can create and modify 3D models through natural language …

Noteblocklib: A Library For Physics- And Animation-Driven Virtual Midi Instruments For Use In Video Games, Kevin Rotunni

Master's Projects

To better capture the relationship between the performer of a piece of music and the music itself in a video game context, I have designed NoteBlockLib, a system by which MIDI instructions are generated and processed in real time based on the motion and collision data of in-game objects. Ultimately, the movement of instruments made using this system would be driven by the animations of a character in the game. This system would thus allow the player character to interact with the performer in the game without sacrificing the relationship between the performer’s actions and the resulting music or to …

Gradual Typing For Information Flow Control In Typescript Using Es Lint, Ashish Agarwal

Master's Projects

Current state-of-the-art systems tackle data security threats by incorporating information flow control (IFC) to ensure that a piece of information reaches only its intended recipient. However, most IFC implementations introduce a custom language built on top of a well-known language. Adaptations of such languages are limited due to limited support and updates, along with difficulty in learning new syntaxes. Implementations without a custom language offer incomplete IFC support. We present a comprehensive framework by leveraging Typescript, in conjunction with ESLint and NodeJS, aiming to resolve some of the limitations of IFC and intending to facilitate acceptance by a wide range …

Adversarial Attacks And Defense Mechanisms In Multivariate Time-Series Forecasting For Applications In Smart And Connected Infrastructures, Pooja Krishan

Master's Projects

The advent of deep learning models has revolutionized the industry over the past decade, leading to the widespread proliferation of smart devices and infrastructures. They play a crucial role in safety-critical applications like self-driving cars and medical image analysis, sustainable technologies like power consumption prediction, and in health monitoring tools to replace industrial equipment like hard disk drives, semiconductor chips, and lithium-ion batteries. But these indispensable deep learning models can be easily fooled to give incorrect predictions with utmost conviction, leading to catastrophic failures in applications where safety is of utmost importance, and resulting in the wastage of resources in …

A Two-Stage Machine Learning Approach For Fake News Detection And News Article Categorization, Snegdha Adusumilli

Master's Projects

This project employs machine learning techniques to develop a sequential model for detecting and categorizing fake news, aiming to mitigate its proliferation in today's digital landscape. The model operates in two phases: in the first phase, the classification algorithms like Naïve Bayes, XGBoost and Random Forest are used to distinguish between true and false news stories and in the second phase the capabilities of Naïve Bayes, XGBoost, Random Forest, and the Transformer-based BERT (Bidirectional Encoder Representations from Transformers) model are leveraged to further categorize the news into specific topics.

The methodology encompasses several key steps: data acquisition, preprocessing, feature extraction, …

Echo: A Browser Extension That Runs Experimental Javascript, Prayuj Pillai

Master's Projects

Narcissus is a JavaScript interpreter written in JavaScript. While it is a good engine for experimenting with JavaScript’s design, it does not integrate easily into the browser. This project introduces ‘‘Echo’’, a browser add-on designed to execute Narcissus JavaScript files and scripts within web browsers. The project explores the performance of the Narcissus interpreter against native browser JavaScript engines and benchmarks the results, showcasing the trade-offs in running an experimental engine—the Narcissus interpreter—on the browser versus native JavaScript. Additionally, as a proof of concept, we implement taint tracking, a capability meant to boost security by preventing sensitive data from being …

Mitigating The Risk Of Reentrancy Attack In Smart Contract Development, Eric Ngo

Master's Projects

Smart contracts, while revolutionizing the blockchain with their immutable nature, are prone to attacks such the reentrancy attack. This attack allows malicious adversaries to repeately enter a contract before previous executions are completed. SpartanScript, a custom dialect of Scheme, is a way for developers to write and develop contracts in an experimental blockchain environment like SpartanGold. Compared to cryptocurrencies that use a virtual machine to run on the blockchain, SpartanScript utilizes a simplified interpreter for rapid prototyping. However, SpartanScript does not have a way to detect and warn developers of reentrancy vulnerabilities. Hence, there is a need to implement reliable …

Secured Data Storage Management With Deduplication In Cloud Computing, Ganesh Regoti

Master's Projects

In the cloud era, cloud storage has become a major service and the security of data and user privacy algorithms are becoming of great importance. This way, we make sure that the encrypted data is kept in the cloud storage. But, the challenges follow: First, storing encrypted data may result in ineffective utilization of cloud resources as in the provision of encrypted data, redundancy cannot be provided. Access control to the encrypted data is difficult as the underlying data is hidden and there is no metric with which the decision to share among users can be easily taken. Deduplication is …

Enhancing Environmental Health And Safety: Fine-Tuning Large Language Models For Domain-Specific Applications, Mohammad Adil Ansari

Master's Projects

This study aims to simplify Environmental Health and Safety (EHS) by leveraging the power of Large Language Models (LLMs). In this research, we focus on fine-tuning three LLMs — LLaMA, Mistral, and Falcon — using PEFT techniques such as QLoRA and SFT, to address domain-specific needs such as safety compliance, incident reporting, and knowledge dissemination. Our research methodology involves fine-tuning each LLM model on a custom dataset compiled from various regulatory agencies, supplemented by targeted web scraping and manual collection of questionnaires to capture and enrich the models with the latest regulations and guidelines. This study aims to compare the …

Resume Content Generation Using Llama 2 With Adapters, Navaneeth Sai Nidadavolu

Master's Projects

The primary objective of this project is to optimize the Llama language model to generate customized resumes containing domain-specific job descriptions and maintain the linguistic capabilities of the large language model. Building upon the prior research by Sumed Kale on Job Tailored Resume content generation using GPT-2, where he employed full fine-tuning of the model and demonstrated the capability of LLMs to generate resume content, it is evident that while effective, full fine-tuning has its limitations. Primarily, it is computationally expensive, which can pose constraints, especially for large models. Additionally, during the fine-tuning process, there is a risk of losing …

Domain Expert Bot, Amrutha Dondemadahalli Ramegowda

Master's Projects

The fast growth of artificial intelligence in human-computer interaction has been aided significantly by the introduction of conversational AI systems. This project presents a Domain Expert Bot, a multi-domain conversational bot built with advanced NLP techniques incorporated through Sentence-BERT and MapReduce to allow the bot to analyze and comprehend challenging user queries on various topics. The bot can converse on different subjects ranging from technology topics to healthcare, environment, politics, and casual discussions. It excels in understanding deep language contexts and efficiently processes large datasets, ensuring prompt and accurate responses. Furthermore, it uses advanced ranking algorithms to perform real- time …

Instagram Data Analysis Using Machine Learning, Lakshmi Prasanna Gorrepati

Master's Projects

With enormous amount of social media content, we can draw valuable insights. In this paper, we apply different Machine Learning and Deep Learning techniques on Instagram data to determine the techniques that work well to discover the engagement class of a social media post. Out of all the social media platforms, Instagram is growing rapidly not just in the number of users but also in terms of Advertisement and marketing surpassing YouTube’s advertisement revenue. The end goal of this paper is to propose a technique to predict the engagement class. We applied Random Forest (RF), Stacking Classifier, Extreme Gradient Boost …