Digital Commons Network^™

Mtu-Llm: Llm-Based Multi-Robot Task Allocation And Path Planning For Heterogeneous Robots In Search And Rescue Operations, Kaushik Kannan, Jungyun Bae

Michigan Tech Publications

Urban Search and Rescue operations after natural disasters involve locating and assisting victims in hazardous environments, which is challenging. Classical Multi-Robot Task Allocation (MRTA) and path planning approaches have been used to deploy heterogeneous robot teams in unsafe areas. However, existing methods often lack focus on workload balance and requirement fulfillment and struggle to generalize across different scenarios. To address these challenges, we propose Multi-robot Task allocation Utilizing LLMs (MTU-LLM), a framework designed to reduce the development time for task allocation and path planning approaches, enabling faster robot deployment. The framework uses an LLM-based “prompt engineering” approach that generates task …

Fedevd: A Federated Road Traffic Event Detector From Social Networks, Ahmad Traboulsi, May Itani, Layal Abu Daher, Ali Haidar

BAU Journal - Science and Technology

The increasing population and the corresponding rise in the number of vehicles, coupled with inadequate public transportation, is increasing the already existing traffic problem. One solution to this problem has been the implementation of Traffic Monitoring Systems (TMS). However, TMS deployment entails significant costs, including (1) the installation of hardware in key areas and (2) the employment of dedicated monitoring personnel. Simultaneously, Online Social Networks (OSNs) have become global platforms with rapidly growing user bases, leading to a surge in user engagement. This widespread participation has transformed social networks into invaluable sources of data for analytics, business intelligence, and decision …

Fuzzy Logic-Based Decision Support System For Adoption Of Industry 4.0 Predictive Maintenance By Manufacturing Industries, Fred E. Peter

Tanzania Journal of Engineering and Technology (TJET)

In the context of Industry 4.0, predictive maintenance enhances operational efficiency by optimizing processes, minimizing downtime, and improving cost-effectiveness. However, implementing predictive maintenance requires a systematic approach due to its complexity. This study collected expert input from 15 food and beverage manufacturing industries located in Dar es Salaam, Tanzania, using a purposive sampling technique. Six representatives were selected from each industry, and their opinions were analyzed using MATLAB 7.6 through a fuzzy logic inference system. The analysis focused on key factors influencing Industry 4.0 technology adoption for predictive maintenance, including adoption intention (strategic decision, equipment data, perceived benefit) and perceived …

Fuzzy-Ahp Based Decision Support System For The Selection Of Optimal Maintenance Strategy For Meter Gauge Railway Infrastructure: A Review, Hamisi J. Maulid

Tanzania Journal of Engineering and Technology (TJET)

There are many uncertainties and complexities associated with maintaining Meter Gauge Railway (MGR) infrastructure, which calls for a methodical approach to decision-making. The development and application of a fuzzy-AHP-based decision support system (DSS) to select the optimal maintenance strategy for the MGR are presented in this study. The review covers research from 2013 to 2023 and focusses on the use of Multi-Criteria Decision Making (MCDM) and Fuzzy Analytic Hierarchy Process (Fuzzy-AHP) techniques in railway infrastructure maintenance. To manage the inherent uncertainties and subjective judgements involved in maintenance decision-making, the Fuzzy-AHP methodology combines fuzzy logic with the Analytic Hierarchy Process (AHP). …

Store-By-Voice: A Voice-Controlled Putaway And Stocktaking System, Thorsten Schmidt, Heiner Ludwig, Mathias Kühn

International Material Handling Research Colloquium

No abstract provided.

Exploring The Potential Of Large Language Models (Llms) To Simulate Social Group Dynamics: A Case Study Using The Board Game "Secret Hitler", Kaj Hansteen Izora, Christof Teuscher

Northeast Journal of Complex Systems (NEJCS)

This study explores the capacity of large language model-powered agents to simulate human-like behavior in multi-agent social systems. Using Secret Hitler — a hidden-role board game centered on trust, deception, and strategic communication — we evaluate how LLM agents navigate dynamic group interactions. Our findings show that agents exhibit human-like behaviors, including strategic temporal adaptation, contextual reasoning, and complex social cognition such as theory of mind and implicit coordination. Notably, 85% of agent decisions factored in at least two other players’ mental states, highlighting their capacity for multi-agent mental state inference. However, they struggled with key aspects of human gameplay, …

Context-Switch Attacks: Understanding And Mitigating The Threat To Llm Applications, Sydney Holder, Bivin Sadler

SMU Data Science Review

Large Language Models (LLMs) are transforming conversational AI, yet their dependence on prompt-supplied context exposes them to context-switch attacks that covertly steer dialogue toward sensitive or malicious ends. A 70 one-sided conversation transcript evaluation set was constructed spanning various fraudulent scenarios. Each transcript embeds adversarial patterns drawn while preserving natural conversational flow. We introduce a hybrid defense that pairs a BERT-based semantic-drift detector (cosine-similarity threshold = 0.70) with a curated keyword and hack-phrase scanner to counter these threats. In aggregate, the system delivered 100 % recall, intercepting every simulated phishing or data-harvesting attempt. The keyword layer achieved perfect precision, generating …

Self Driving Robot Car, Eric Hicks, Ruby Huynh

Computer Science and Engineering Senior Theses

In the real world, vehicular crashes are the result of human error and inadequate reaction time and are often deadly. Due to the issue of accidents being frequent occurrences, using machine learning to drive vehicles has quickly become a relevant topic as it could potentially become a way to minimize fatalities and damages. Thus, the project aims to approach self-automation with the focus on maximizing the vehicle’s performance and the machine’s ability to make the best decisions within that time.

Today’s self-driving cars use radar or cameras as well as digital signal processing algorithms to sense the environment while using …

A Universal Lstm Stock Price Predictor Utilizing News Sentiment Analysis And Technical Indicators, Kelly Zhou, Zhirong Wang

Computer Science and Engineering Senior Theses

The stock market is influenced by a complex interplay of factors, including historical price trends, technical indicators, news sentiment, and macroeconomic conditions. Traditional stock prediction models typically focus on a single stock, limiting their ability to capture broader market relationships. Investors require a model that can accurately forecast price movements across multiple stocks to optimize trading decisions.

We propose a universal stock prediction model that leverages relationships across all S&P 500 stocks. Unlike traditional single-stock models, our approach utilizes a multi-stock LSTM architecture trained on a combination of historical stock prices, technical indicators, and news sentiment. The model is designed …

Preserving Yucatán’S Agricultural Heritage: A Mobile App For Agricultural Sustainability, Fernando Rojas, Jason Serrano, Kavya Sharma

Computer Science and Engineering Senior Theses

We developed a mobile application that preserves Yucatán’s agricultural heritage and supports local farmers, while addressing the urgent need for the technology-driven integration of Mayan agricultural knowledge, specifically the Milpa system, into an accessible mobile platform. Our objective was to create an intuitive, culturally appropriate, and low-technology resource to support farmers in making informed, sustainable agricultural decisions, regardless of their internet connection. We saw this as critical for enhancing agricultural practices in Yucatán and beyond. We accomplished this by creating a trilingual (Spanish, English, and Yucatec Maya) mobile app with features such as agrarian cycle information, mapping and location services, …

Bilingual Buddy, Adian Alvarado, Farhaan Pishori, Luis Villalta, Andrea Yao, Ekam Singh

Computer Science and Engineering Senior Theses

Bilingual students often face challenges in mathematics not due to a lack of ability, but because of linguistic barriers that hinder their understanding of math-specific terminology and consequently their problem-solving language ability. This project addresses that issue through the development of a mobile application designed to support English language acquisition in the context of mathematics for Spanish-speaking students. Rather than teaching mathematical concepts directly, the app focuses on vocabulary, syntax, and contextual comprehension through scaffolded lessons, gamified elements, and an integrated AI chatbot.

Built using Flutter for cross-platform compatibility, the app prioritizes accessibility, simplicity, and engagement for young users. Ethical …

Online Hyperparameter Tuning For Llm Optimization, Ethan Lin, Nathan Yu, Jeromy Chang

Computer Science and Engineering Senior Theses

Large Language Models (LLMs) are becoming increasingly popular in modern society. However, despite their popularity, the deployment of LLMs in real-world scenarios is extremely challenging due to substantial computational costs and memory constraints. Edge devices, like smartphones and IoT devices, lack resources needed to run these models locally, instead offloading computations for cloud computing. Cloud computing requires users to send their data over the internet leading to numerous privacy and security concerns. In some domains, such as health and finances, sending such sensitive information is not an option. Existing solutions to compress or increase inference speed include Small Language Models …

Detection Of Fake News In Short Videos: A Multimodal Approach, Mona Kumari

Master’s Dissertations

The rise of generative models and affordable video editing tools has fueled the spread of fake and manipulated videos, undermining information reliabilityespecially on social media. Traditional detection methods, focused on single modalities like visual artifacts or text cues, often struggle with diverse, user-generated content. This dissertation presents a unified framework for fake video detection that integrates multimodal semantics, narrative structure, and propagation behavior. Visual, audio, text, and OCR features are extracted using pretrained models (CLIP, Wav2Vec2), and segment-level graphs are built to model narrative flow using Graph Attention Networks (GATv2Conv). User engagement dynamics are modeled via a bidirectional LSTM. A …

Emg Vocal Translations, Lucas Amlicke, Raphael Kusuma, Cole Heider, Kayleigh Vu, Monica Sommer

Electrical and Computer Engineering Senior Theses

In this paper, we propose a novel augmentative and alternative communication (AAC) framework for silent speech. Many individuals with speech impairments are unable to vocalize effectively due to various conditions that affect the vocal cords. To engage in social activities, many rely on AAC devices that often lack flexibility and expressiveness. Users may still find self-expression and spontaneity difficult with such devices. This project presents a novel approach to developing a silent speech interface (SSI), providing a more adaptable and user-centered solution to give the vocally impaired a voice. Using surface electromyography (sEMG) alongside machine learning techniques, we aim to …

Synergizing Stem And Ela: Exploring How Small-Group Interactions Shape Design Decisions In An Engineering Design-Based Unit, Deana Lucas, Emily Haluschak, Christine H. Mcdonnell, Selcen Guzey, Greg J. Strimel, Morgan Hynes, Tamara J. Moore

School of Engineering Technology Faculty Publications

While small group learning through engineering design activities has been shown to enhance student achievement, motivation, and problem-solving skills, much of the existing research in this area focuses on undergraduate engineering education. Therefore, this study examines how small-group interactions influence design decisions within a sixth-grade engineering design-based English Language Arts unit for multilingual learners. Multilingual Learners make up 21% of the U.S. school-aged population and benefit from early STEM opportunities that shape future educational and career trajectories. Grounded in constructivist learning theories, the research explores collaborative learning in the engineering design process, using a comparative case study design. Specifically, this …

Control Strategies In Wind Energy Systems: A Comprehensive Overview, Abeer Awad, Mohamed Al Hasheem

Future Engineering Journal

This paper reviews different control methods used in wind energy systems to improve how they work and connect to the power grid. It covers simple control methods like Proportional-Integral (PI) controllers, as well as more advanced ones like Sliding Mode Control and intelligent controls such as fuzzy logic and neural networks. The strengths and weaknesses of each method are discussed, focusing on how well they handle changes in wind and load, keep power quality high, and stay stable. Challenges like system complexity and unpredictable wind are also explained. The paper ends by suggesting that future work should focus on combining …

Portuguese For Mozambican Mothers – A Language Empowerment App, Josh Kindarara, Alexandre Lopes, Gwendolyn Patwardhan, Riana Santos, Sara Wheeler

Computer Science and Engineering Senior Theses

In Mecúfi, Mozambique, the mothers of children who attend school through the DIFF EDUCATION program have a strong desire to learn Portuguese, the country’s national language, due to colonization. However, they have minimal formal education and little to no experience with technology. They are unable to read or write in any language, including their native language, Makhuwa, making many current educational resources unusable. This leaves these mothers without accessible, culturally relevant tools to help address their linguistic needs.

This project focuses on developing an educational application designed for non-literate mothers in rural Mozambique. The app emphasizes visual and auditory learning …

Optical Character Recognition For Early Handwriting Legibility Assessment, Franceli L. Cibrian, Kayla Anderson, Yingying 'Yuki' Chen, Lauren Min, Lizbeth Escobedo

Engineering Faculty Articles and Research

Monitoring children’s handwriting, such as avoiding writing assignments, displaying uneven letter formation, or showing slow writing speed, can help identify developmental and academic issues early. Poor handwriting affects up to 34% of children, leading to academic and self-esteem challenges. Handwriting assessments, typically conducted by teachers, are often delayed due to workload and could be subjective and inconsistent. This paper explores the potential of Optical Character Recognition (OCR) technology to augment and ease handwriting assessments. Based on an evaluation of 10 OCR algorithms using 33 handwriting samples assessed by two experts, the research indicates that Pen to Print and Google are …

Data-Driven Product Recommendations: A Decision Support Framework Utilizing Customer Reviews, Tyler A. Lopez

Master's Theses

With the considerable presence of e-commerce in society, vast number of purchasable goods, and increasing brand variety, consumers are faced with the challenge of buying products that they perceive to be of greatest value to them. To assist consumers with making better informed decisions, e-commerce websites allow individuals to post their own experiences and score the products that they purchase. Despite this information, the variety of experiences and feedback that consumers share do not always lead to clarity on whether a product is best suited for the purchaser. To help guide customers through a simplified purchasing process from the perspective …

A Predictive Model For The Shear Capacity Of Ultra-High-Performance Concrete Deep Beams Reinforced With Fibers Using A Hybrid Ann-Anfis Algorithm, Hossein Mirzaaghabeik, Nuha S. Mashaan, Sanjay Kumar Shukla

Research outputs 2022 to 2026

Ultra-high-performance concrete (UHPC) has attracted considerable attention from both the construction industry and researchers due to its outstanding durability and exceptional mechanical properties, particularly its high compressive strength. Several factors influence the shear capacity of UHPC deep beams, including compressive strength, the shear span-to-depth ratio (λ), fiber content (FC), vertical web reinforcement (ρsv), horizontal web reinforcement (ρsh), and longitudinal web reinforcement (ρs). Considering these factors, this research proposes a novel hybrid algorithm that combines an adaptive neuro-fuzzy inference system (ANFIS) with an artificial neural network (ANN) to predict the shear capacity of UHPC deep beams. To achieve this, ANN and …

A Neutrosophic And Q-Rung Orthopair Fuzzy Sets Approach For Desertification Susceptibility Mapping: A Case Study In Matrouh, Egypt, Nabil M. Abdelaziz, Khalid A. Eldrandaly, Amira M. Fawzy, Gehan A. Fouad, Safa Al-Saeed

Neutrosophic Systems with Applications

This study introduces an innovative approach to desertification susceptibility mapping by integrating q-rung orthopair fuzzy sets (Q-ROFS) with a neutrosophic environment. Conducted in Matrouh, Egypt, the research quantifies desertification risk through advanced modeling techniques that address uncertainty and non-linearity in environmental data. The Q-ROFS framework enhances risk prediction by capturing complex relationships among desertification indicators. Neutrosophic logic, meanwhile, effectively addresses imprecision and ambiguity. The resulting susceptibility map clearly distinguishes between vulnerable and non-vulnerable regions, offering valuable guidance for policymakers and planners. The analysis revealed that approximately 79.98% of the study area falls under moderate susceptibility, 14.27% under high susceptibility, and …

A Critical Evaluation Of The Criticisms Against Neutrosophic Statistical Methods, Muhammad Aslam, Abdulrahman Alaita, Florentin Smarandache

Neutrosophic Systems with Applications

Neutrosophic statistical analysis has gained attention for incorporating the degree of indeterminacy when analyzing imprecise and interval data under uncertainty–-an aspect often overlooked by classical statistics, fuzzy statistical analysis, and interval statistics. Recently, critical discussions have emerged regarding the use and applications of neutrosophic statistics, with some questioning its usefulness and validity. In this paper, we present a critical assessment of the existing literature, focusing on areas where misunderstandings and misinterpretations of neutrosophic statistical methods have occurred. We also examine flawed comparisons made between the results of neutrosophic statistics and interval statistics. Furthermore, substantial issues have been identified in the …

Contract Quality Feature Extraction Using Llm, Aaron C. Washington

Theses and Dissertations

This study explored the potential insights generated from linguistic complexity measurements and large language model (LLM) based assessments on the quality of contract documents. By combining structured True/False prompts with log-probability analysis and ambiguity scoring, the study introduced novel contract-quality assessment methods. Results support a feature-driven approach to contract evaluation, one that offers automated, scalable insights for triaging risk and improving drafting practices. These assessment methods contribute to the growing field of legal natural language processing by offering modular tools for effective contract analysis.

Meta-Learning Hyperparameters For Foundation Model Adaptation In Remote-Sensing Imagery, Zichen Tian, Yaoyao Liu, Qianru Sun

Research Collection School Of Computing and Information Systems

Training large foundation models of remote-sensing (RS) images is almost impossible due to the limited and long-tailed data problems. Fine-tuning natural image pre-trained models on RS images is a straightforward solution. To reduce computational costs and improve performance on tail classes, existing methods apply parameter-efficient fine-tuning (PEFT) techniques, such as LoRA and AdaptFormer. However, we observe that fixed hyperparameters -- such as intra-layer positions, layer depth, and scaling factors, can considerably hinder PEFT performance, as fine-tuning on RS images proves highly sensitive to these settings. To address this, we propose MetaPEFT, a method incorporating adaptive scalers that dynamically adjust module …

Adversarial Robustness In Advanced Machine Learning Models Integrating Graph Neural Networks And Large Language Models, Mahmoud Nazzal

Dissertations

Artificial intelligence (AI) has achieved remarkable performances across various domains. In most real-world applications, data often takes relational forms, such as graphs and networks, or sequential forms, such as text and time series. As AI evolves, specialized models have emerged to handle these structures; Graph Neural Networks (GNNs) for relational mining and Large Language Models (LLMs) for sequential understanding. Despite their success, these models face challenges in security, robustness, and interpretability. GNNs excel in relational reasoning but are vulnerable to adversarial manipulation and lack interpretability, while LLMs are strong in linguistic reasoning and generalization yet struggle with relational data and …

Designing Between Worlds, Levon Kostandyan

Masters Theses

This thesis reimagines design as a means of cultural continuity—an act of memory, resistance, and transformation. Rooted in the diasporic Armenian experience, it explores how identity is carried not only through storytelling, but through materials, rituals, and objects that evolve across time and place. Through the transformation of pomegranate skin from waste into a meaningful design material, the project navigates the space between symbolism and substance, honoring both the fruit’s ancestral weight and its potential as a living material language.


The work moves between personal narrative, historical research, and material experimentation, engaging with themes of displacement, hybridity, and embedded knowledge. …

Comprehensive Risk Assessment Of Power Grids Using Fuzzy Bayesian Networks Through Expert Elicitation: A Technical Analysis, Yasir Mahmood, Nof Yasir, Nita Yodo, Ying Huang, Di Wu, Roy A. Mccann

Electrical Engineering and Computer Science Faculty Publications and Presentations

Power grid infrastructures, essential to modern societies for electricity distribution, are prone to vulnerabilities due to their numerous sensitive components, necessitating a comprehensive risk assessment. Uncertainty in historical failure data often compromises accurate risk quantification, leading to the integration of expert elicitation as a solution. This study develops a Bayesian network (BN) risk assessment model integrated with fuzzy set theory (FST), referred to as the fuzzy Bayesian network (FBN). By incorporating expert insights, this model quantifies internal and external risk variables more comprehensively. Crisp probabilities (CPr), derived from regional transmission operator (RTO) failure incident data, are complemented by fuzzy probabilities …

Integrating A Stakeholder-Centric Approach Into Dynamic Adaptation Policy Pathways For Equitable Coastal Flood Risk Management In East Boston, Shailee M. Desai

Graduate Doctoral Dissertations

This research aims to illustrate a methodology incorporating diverse stakeholder values in adaptation planning to promote equitable outcomes using a hypothetical case study of the Lower Border Street area in East Boston, using the Dynamic Adaptive Policy Pathways (DAPP) framework for managing coastal flood risk. It offers three significant contributions to the field of adaptation planning: (i) It demonstrates how to integrate a stakeholder-specific assessment within the DAPP framework and illustrates individual impacts to a variety of stakeholders, including high- and low-income residents, commercial actors, government actors, and coastal landowners hoping that the planning process remains transparent and motivates local …

Retracted: A Group Decision-Making For Selecting Multi-Deep Face Recognition Models, Abdulbasit Alazzawi, Qahtan M. Yas, Burhan Albayati

Iraqi Journal for Computer Science and Mathematics

Deep face recognition is a significant area of biometric authentication that addresses challenges such as low resolution, varying facial expressions, and inconsistent lighting. This paper presents a robust deep-learning approach to tackle these challenges. The study aims to employ multi-criteria decision-making techniques and verify the influence of individual and group expert opinions in decision-making. However, balancing criteria such as accuracy, sensitivity, specificity, precision, and recall remain challenging across different models. To fill this gap, the study utilized a decision-support framework that included the fuzzy analytical hierarchical process to set criteria weights based on expert input and the Technique for Order …

Probabilistic Cash Flow Analysis Considering Risk Impacts By Integrating 5d-Building Information Modeling And Bayesian Belief Network, Mohammad Hosein Madihi, Mohammadsoroush Tafazzoli, Ali Akbar Shirzadi Javid, Farnad Nasirzadeh

Civil Engineering & Construction: Faculty Publications

Unrealistic cash flow forecasts negatively affect project stakeholders and are a common issue for construction practitioners. This study proposes a new method for predicting the probabilistic cash flow of a project that can automate the calculation process while considering the impact of risks and their inter-related structure. This research integrates a Bayesian Belief Network (BBN) and 5D-BIM to provide a new probabilistic cash flow analysis approach. Here, 5D-BIM is used to facilitate cash flow calculations and automate the process. The BBN has also been implemented to assess the impact of risk factors on project cash flow, considering their complex inter-related …