Digital Commons Network^™

Skin Cancer Detection Using Reinforcement Learning, Vikas Chercadu

Master's Projects

Advances in medical diagnostics have increasingly harnessed the power of artificial

intelligence, offering substantial improvements in early and accurate disease identifi- cation. This paper elaborates on a novel integration of Multi-Agent Reinforcement

Learning (MARL) with Deep Learning for the early detection of skin cancer, one of the most prevalent and lethal forms of cancer when left unchecked. Our project capitalizes on the sophisticated VGG16 Network for the extraction of detailed features from the widely-utilized HAM10000 dermatoscopic dataset, enhancing these features with additional color, texture, and shape analysis. Utilizing a custom-designed MARL environment, we facilitate a collaboration among multiple intelligent agents, …

Mitigating Learning Bias In Healthcare Datasets, Samyak Jagdish Kumbhalwar

Master's Projects

CVDs have been a major cause of deaths worldwide with WHO reporting 17.9 million deaths annually. Although there are advancements in the treatment of these diseases, most of the fatalities are a result of untimely diagnosis. Active research is going on to collect data points and risk factors related to these diseases, which can enable early diagnosis. Of the datasets available, many researchers have employed different ML models to predict/detect the prevalence of heart diseases. Many employed Tree based, regression models [3, 6]. Few also tried ensemble approaches [1, 2, 4]. These healthcare datasets are generally found to be imbalanced. …

Understanding Distracted Driving And Gaze Patterns In A Driving Simulator: Simple Vs. Complex Challenges, Rishi Prabhat Narayana Sannala

Master's Projects

Distracted driving has grown in criticality over the recent years, given the numerous distractions that drivers face today, and which have further been magnified by the proliferation of in-vehicle technologies and mobile devices. Such distractions can seriously compromise a driver's ability to be fully focused on the road and to carry out timely responses and informed decisions that are key in minimizing the risks of a crash and maximizing road safety. The general aim of the research is to observe how simple versus complex distractors affect driving performance and gaze patterns. The eyetracker used is the Tobii Pro Fusion, synchronized …

Hindi Image Captioning Using Indictrans2 And Encoder-Decoder Architecture, Anahita Vayalombrone Dinesh

Master's Projects

One of the most prominent tasks that lie on the conjunction of Natural Language Processing (NLP) and computer vision, is image captioning. Image captioning is the generative task of achieving textual descriptions from images. Its application finds use in many real-world scenarios like aiding the visually impaired, editing applications, recommendation systems, and medical imaging. This research focus lies in Hindi image captioning, the official language of India, as it has not been explored as far as its need. Several challenges such as the lack of substantial Hindi text data for training models, the need for human annotators to verify the …

A Rule-Based Hybrid Translation Model For Context-Aware Speech To Indian Sign Language Tasks, Dania Jaison

Master's Projects

In India, one of the most significant tools to communicate with the Deaf and Hard of Hearing (DHH) communities is Indian Sign Language(ISL). The issue of a scarcity of computational resources for ISL is even more pronounced when it comes to the translation of written or spoken English into ISL. This paper proposes a rule-based model for translation where the spoken english sentences are translated into ISL by focusing on the specific syntactic and grammatical differences between these two languages. ISL uses a simplified syntax unlike the nuanced sentence structures in English — we omit most of the auxiliary verbs …

Multimodal Emotion Detection In Conversations And Dialogues: A Fusion Model Approach, Abhinay Jatoth

Master's Projects

Emotion recognition is gaining traction due to its wide range of potential applications across different fields. With the rise of social media, chat platforms, and voice assistants, there is a vast increase in data through which humans implicitly and explicitly carry emotional cues. With new algorithms being developed for understanding the nuances of human language and emotion, businesses can tailor more personalized and empathetic service. Sentiment analysis, expresses a positive, negative, or neutral viewpoint laid the foundation of Emotion classification. Emotion classification in conversations represents the most advanced stage of classification. It is also challenging due to the existence and …

Lexigen: Lexical-Driven Image Generation, Sangram Prashant Chincholkar

Master's Projects

This research project proposes a novel approach to user-driven image editing via natural language descriptions. The aim is an accurate change of certain features of an image with respect to the descriptive text while maintaining, with equal concern, the integrity of the remaining parts of the image not affected by the description. The task is particularly relevant for fields like content creation, personalized design, and automated image editing that require both coherence of a visual scene and textual description. We propose a generative model, LexiGen, which perfectly integrates natural language descriptions with their corresponding visual changes within an image. The …

Personalizing Image Generation From Prompts Using Generative Ai, Mit Ramesh Jain

Master's Projects

The rapid advancements in Generative AI, particularly Text-to-Image (T2I) models, have opened up new possibilities for personalized image generation. Finetuning large T2I models for specific downstream tasks is a key approach to achieving tailored outputs. In recent years, Parameter-Efficient Fine-Tuning (PEFT) techniques have gained significant attention as a cost-effective and efficient solution for fine-tuning large models. Initially developed for fine-tuning large language models (LLMs), PEFT techniques have been extensively studied and compared in the context of language tasks. However, regarding the T2I domain, there is a lack of similarly exhaustive and detailed literature on PEFT. This research project, in the …

Load Balancing For Cloud-Based Applications, Nitish Ranjan

Master's Projects

Effective load balancing is critical in ensuring optimal resource utilization, reducing latency, and improving the overall performance of distributed systems. This report commences with a comprehensive literature review on existing load-balancing algorithms, examining their methodologies, strengths, and limitations within various computing environments, including cloud computing, data centers, and network traffic management. Despite significant advancements in this field, the dynamic nature of distributed systems, coupled with the ever-increasing demand for efficient data processing, poses ongoing challenges. In response, this study proposes a novel load-balancing algorithm to address these contemporary challenges. The approach leverages dynamic and hybrid load balancing, distinguishing it from …

Exploring The Use And Misuse Of Large Language Models (Llms), Hezekiah Paul D. Valdez

Master's Projects

Large Language Models (LLMs) have quickly gone from simple rule-based systems to complex knowledge bases capable of tackling many different tasks across a variety of fields. What began as an exercise in human-computer interaction has become the basis for artificial intelligence in a variety of mediums. When attached to larger systems, LLMs become generative assistants that can perform highly on human proficiency assessments and other benchmark skill assessments. This increase in proficiency has led these systems to be deployed in fields such as cybersecurity, business, and programming to help improve productivity and efficiency. However, such a wide availability has allowed …

Code Quality Enhancement: Evaluating Ai Code Generation With Software Metrics, Sirisha Krishna Murthy

Master's Projects

With the advancements in the stream of AI in the recent time and the evolution of Generative AI, it is a given that there is a need to effectively integrate AI into daily tasks, including Coding. When talking about Generative AI, one important thing to consider is prompting, which is that way to talk to the AI. Depending on specific needs and tasks the way we need to prompt AI can vary. With rapid development in the field, there are a lot of new benchmarks that evaluate the AI coders on correctness, but to effectively adapt AI into actual coding …

Enhancing Qwen2.5-Coder: A Deep Dive Into Fine-Tuning Using Peft For Superior Code Outputs, Lohith Nagaraja

Master's Projects

The main objective of this research is to improve the quality of software code that is produced by the Qwen2.5-Coder model specifically in terms of maintainability, complexity, and reliability. Our approach is going to be a more specific one that will involve the Parameter-Efficient Fine Tuning (PEFT) framework combined with quantization through Low-Rank Adaption (LoRA). This approach involves fine-tuning only some of the parameters of a model to make it suitable for software programming with the general structure of the model largely intact. In this paper, SonarQube is used as a tool to help quantify the improvements made to the …

Enhanced Inter-Satellite Routing With Multi-Path Selection And Congestion Modeling, Jaesung Yoo

Master's Projects

Satellite networks play a crucial role in global connectivity today and making efficient routing algorithms is crucial for optimal performance. While existing routing algorithms have made significant progress using machine learning techniques, they often overlook network congestion and multiple path availability. This report introduces an enhanced routing framework that builds upon LSTM-based predictive routing using dynamic congestion modeling and multi-path selection. Our approach introduces a busy state metric that tracks satellite memory utilization, allowing for adaptive path selection based on both distance and current network load. Through simulations using a constellation of 20 satellites, our enhanced algorithm demonstrates significant improvements …

Optimizing Web Design Code Generation: A Comparative Study Of Finetuning, Pretrained Models, And Rag (Retrieval Augmented Generation), Srinivas Rao Chavan

Master's Projects

Website Creation is revolutionized by automated code generation, reducing the development effort, speeding the production process, and ensuring consistency in design. Automated web design code generation has emerged as a transformative tool bridging the gap between design and development. In this research, a website design tool is developed and used to create visual layouts, exporting them as JSON designs. These JSON outputs were then transformed into textual prompts, optimized using established HCI principles and UI/UX rules to ensure consistency, visual hierarchy, aesthetics and minimalistic design, accessibility, user-friendly navigation and flexibility. These generated prompts were fed into large language models for …

Teaching Children Programming Concepts Through Video Games, Kayla Musleh

Master's Projects

Children have a tendency to lose focus when they are presented with something that does not entertain them or tailor to their personal interests; such as studying [1], [3], [10]. The research performed for this project focuses on studying how much more children can comprehend and focus on learning educational material if they are learning through playing a video game rather than being taught information directly in a typical classroom manner. For this study I created a computer game designed to introduce educational subjects such as mathematics and programming concepts to the child playing the game. By completing the tasks …

Creating Valid Adversarial Examples Of Malware, Matouš Kozák, Martin Jureček, Mark Stamp, Fabio Di Troia

Faculty Research, Scholarly, and Creative Activity

Because of its world-class results, machine learning (ML) is becoming increasingly popular as a go-to solution for many tasks. As a result, antivirus developers are incorporating ML models into their toolchains. While these models improve malware detection capabilities, they also carry the disadvantage of being susceptible to adversarial attacks. Although this vulnerability has been demonstrated for many models in white-box settings, a black-box scenario is more applicable in practice for the domain of malware detection. We present a method of creating adversarial malware examples using reinforcement learning algorithms. The reinforcement learning agents utilize a set of functionality-preserving modifications, thus creating …

Fuzzy Similarity Analysis Of Effective Training Samples To Improve Machine Learning Estimations Of Water Quality Parameters Using Sentinel-2 Remote Sensing Data, Alireza Taheri Dehkordi, Mohammad Javad Valadan Zoej, Ali Mehran, Mohsen Jafari, Amir Masoud Chegoonian

Faculty Research, Scholarly, and Creative Activity

Continuous monitoring of water quality parameters (WQPs) is crucial due to the global degradation of water quality, primarily caused by climate change and population growth. Typically, machine learning (ML) models are employed to retrieve WQPs, but they require a large amount of training samples to accurately capture the data relationships. Even with sufficient training data, discrepancies still exist between values of predicted and in-situ WQPs. This study proposes a fuzzy similarity analysis (FSA) technique to enhance ML estimates of WQPs by using the prediction errors in effective training samples. The method was successfully applied to retrieve turbidity (Turb) and specific …

Selective Partitioned Regression For Accurate Kidney Health Monitoring, Alex Whelan, Ragwa Elsayed, Alessandro Bellofiore, David C. Anastasiu

Faculty Research, Scholarly, and Creative Activity

The number of people diagnosed with advanced stages of kidney disease have been rising every year. Early detection and constant monitoring are the only minimally invasive means to prevent severe kidney damage or kidney failure. We propose a cost-effective machine learning-based testing system that can facilitate inexpensive yet accurate kidney health checks. Our proposed framework, which was developed into an iPhone application, uses a camera-based bio-sensor and state-of-the-art classical machine learning and deep learning techniques for predicting the concentration of creatinine in the sample, based on colorimetric change in the test strip. The predicted creatinine concentration is then used to …

Forced Labor And Transportation: Multi-Disciplinary Perspectives, Kezban Yagci Sokat, Marisa Auguste, Christi Wigle, Chris Baglin

Faculty Research, Scholarly, and Creative Activity

Transportation plays a key role in combating human trafficking. This paper discusses data from the 2021 National Outreach Survey for Transportation (NOST), from the first ever United States Department of Transportation Combating Human Trafficking in Transportation Award winning project. Survey data collected from transportation personnel, victim service providers, and trafficking survivors reinforces the documented perceptions, limitations, and challenges in understanding and combating forced labor discussed among frontline workers. Among 173 respondents working in various state DOT construction units, only 26 % feel slightly or very confident (19 % and 7 %, respectively) about identifying labor trafficking in their work environment. …

Conditional Variational Transformer For Bearing Remaining Useful Life Prediction, Yupeng Wei, Dazhong Wu

Faculty Research, Scholarly, and Creative Activity

Transformer, built on the self-attention mechanism, has been demonstrated to be effective in numerous applications. However, in the context of prognostics and health management, the self-attention mechanism in the Transformer is not effective in selecting the most important features that are highly correlated with the remaining useful life (RUL) of a component. To address this issue, we developed a novel conditional variational transformer architecture consisting of four networks: two generative networks and two predictive networks. The first generative network uses the transformer encoder–decoder as well as both condition monitoring data and RUL as input to extract the most important features …

Emf Revisited, Art Davis

Faculty Research, Scholarly, and Creative Activity

This paper was inspired by a recent publication by Redžíc (2018 Eur. J. Phys. 39 025205) which threw into bold relief the differences between the way Maxwell viewed the current and the way Lorentz visualized it. We make the assumption that for a circuit of laboratory dimensions current (and charge perturbation effects in general) can be assumed to propagate instantaneously around the loop. Our second fundamental assumption is the commonly accepted one that E is the force per unit charge on a stationary charge. We use these facts to make the usual definition of electromotive force more rigorous and to …

Enhancing Diagnostic Accuracy: A Hybrid Approach To Mitigate Speckle And Rician Noise In Medical Images, Naveenkumar Jayakumar, Saurabh Saoji, Sagar V. Joshi, Hemlata Mane, Roshni Narkhede, Shrikant Jadhav

Faculty Research, Scholarly, and Creative Activity

This research explores the detrimental effects of Rician and speckle noise in medical imaging, particularly within MRI and radiographic modalities. Such noise can significantly obscure critical details, potentially leading to misdiagnoses and inaccurate measurements. Rician noise candidly dangles on the signal strength. Removing this noise affects the origial information in image that makes this noise removal perplexing. On other hand speckle noise is visualised like granular clog in ultrasound imageries. It creates ambiguous details and edges in the images. To address this challenge, the study introduces a novel hybrid method implemented in Java. The method employs a frequency-based decomposition approach …

Enhancing Product Designing With The Help Of Artificial Intelligence, Dhyeykumar Nikalwala, Minnie H. Patel

Faculty Research, Scholarly, and Creative Activity

In the ever-changing world of Business, making a successful product design requires quickly trying out new ideas and listening to what users think. With the integration of Artificial Intelligence (AI), the process of rapidly generating content from existing data becomes easier, accelerating the creation of innovative product concepts. To use this cutting-edge technology to build novel products a framework is essential. The paper aims to propose a novel framework that caters to a customer-centric integration of AI in Product Design. The paper goes beyond theoretical explanation, implementing the framework to iteratively design 3 diverse products. The implementation also highlights the …

Eyes On Higher Education: Evaluating Web Usability In Kuwaiti Private Universities Using Eye-Tracking And Supr-Q Metrics, Reem Albaghli, Ayah Beidas, Nada Attar

Faculty Research, Scholarly, and Creative Activity

Website design and usability are critical factors that impact the effectiveness of a website, influencing both user attraction and retention. Understanding user preferences is essential for designers and researchers when optimizing user interfaces (UI) and user experiences (UX). This study addressed key research questions about usability by examining which design heuristics have the most impact on students’ interactions with private university websites in Kuwait. By assessing web design and usability across three private universities in Kuwait through specific tasks, we analyzed user experiences using eye-tracking data, task completion times, user inputs, and qualitative feedback from the Standardized User Experience Percentile …

Navigating Enterprise Constraints: Building A Hybrid Multi-Modal Mobile Intelligent App, Ketan Malempati, Akshat Gupta, Kaikai Liu

Faculty Research, Scholarly, and Creative Activity

The promise of artificial intelligence (AI) has prompted various industries to explore how it can enhance their businesses and improve customer experiences. However, the practical deployment of AI services faces challenges due to internal infrastructure limitations, data policies, and network restrictions. In this paper, we present our current project - a solution designed to empower mental health centers with AI tools while adhering to stringent data and network constraints. Our approach involves deploying AI services and data within internal enterprise networks, while the customer-facing mobile app resides in the public cloud. We introduce a custom AI agent system that monitors …

Next Steps For Assessing Ocean Iron Fertilization For Marine Carbon Dioxide Removal, Ken O. Buesseler, Daniele Bianchi, Fei Chai, Jay T. Cullen, Margaret Estapa, Nicholas Hawco, Seth John, Dennis J. Mcgillicuddy, Paul J. Morris, Sara Nawaz, Nishioka, Anh Pham, Kilaparti Ramakrishna, David A. Siegel, Sarah R. Smith, Deborah Steinberg, Kendra A. Turk-Kubo, Benjamin S. Twining, Romany M. Webb

Faculty Research, Scholarly, and Creative Activity

There are many potential approaches to marine carbon dioxide removal (mCDR), of which ocean iron fertilization (OIF) has the longest history of study. However, OIF studies to date were not primarily designed to quantify the durability of carbon (C) storage, nor how wise OIF might be as an mCDR approach. To quantify C sequestration, we introduce a metric called the “centennial tonne,” defined as 1,000 kg of C isolated from atmospheric contact for on average at least 100 years. We present the activities needed to assess OIF from a scientific and technological perspective, and additionally, how it might be responsibly …

Optimal Tool Path For Extrusion-Based Additive Manufacturing To Improve Geometrical Accuracy And Productivity, Robert Ehlers, Amir Armani

Faculty Research, Scholarly, and Creative Activity

The objective of this study was to improve the geometrical accuracy and productivity of extrusion-based additive manufacturing processes. Four algorithms were developed to adaptively change the track width in each layer (i.e., adaptive rastering); optimize the rastering orientation for each layer; adaptively change the layer thickness (i.e., adaptive slicing); and optimize the overall orientation of part. These algorithms were implemented in a commercial 3D printer and several case-studies were conducted to examine their efficacy (individually and combined). The results were compared with standard tool path planning software and indicated a significant improvement in both geometrical accuracy and productivity.

Tcad Structure Input File Generation Using Large Language Model, Le Minh Long Nguyen, Albert Lu, Hiu Yung Wong

Faculty Research, Scholarly, and Creative Activity

In this paper, we study the possibility of using Large Language Models (LLMs) to create Technology Computer-Aided-Design (TCAD) structure generation input files. LLMs are machine learning models trained on vast amounts of text data from the Web and are designed to understand, generate, and interact with humans through natural languages such as English. However, unlike programming languages with abundant training examples on the Web, TCAD examples are scarce. In this work, by using TCAD Sentaurus Structure Editor (SSE) as an example, 7000 nanowire data are generated to fine-tune open-source models (Llama 2 and 3) to obtain chatbots that can generate …

Youth Experiences In Gender–Sexuality Alliances Predict Academic Engagement But Not Disaffection Through Social–Emotional Wellbeing, V. Paul Poteat, Jerel P. Calzo, Hirokazu Yoshikawa, Daniel Kellogg, Robert A. Marx, Abigail Richburg, Arthur Lipkin

Faculty Research, Scholarly, and Creative Activity

Experiences in gender–sexuality alliances (GSAs) could predict youth's academic engagement through improved social–emotional wellbeing (indicated by school belonging, hope, and positive and negative affect). This study utilized three waves of data, each spaced 2–3 months apart, among 627 youth (87% LGBQ+, 45% trans/nonbinary, 48% youth of color) ages 11–22 (Mage = 15.13) in 51 GSAs in the United States in 2021–2022. Greater peer responsiveness in the GSA predicted increased academic engagement through increased wellbeing overall and specifically through hope and decreased negative affect. Advisor responsiveness and GSA leadership correlated with wellbeing and academic engagement in bivariate analyses but were not …

Multi-Robot Source Seeking And Field Reconstruction Of Spatial-Temporal Varying Fields, Deepak Talwar, Thinh Lu, Divyam Sobti, Wencen Wu

Faculty Research, Scholarly, and Creative Activity

To effectively respond to environmental disasters, real-time monitoring and pollution control rely heavily on the ability to estimate, predict, and reconstruct constantly changing environmental conditions across different locations. In this research, we develop a multi-robot source-seeking and field reconstruction framework that enables a multi-robot group to detect multiple sources within a spatial-temporal varying field and reconstruct the field in real time. The strategy consists of two parts: source seeking and field reconstruction. The source-seeking part features a gradient-based source-seeking controller that directs the multi-robot group toward local sources and a destination selection algorithm that navigates the multi-robot formation beyond the …