Computer Sciences Commons^™

Modeling And Simulation Of Complex Systems Based On Graph Neural Networks, Jinhu Lü, Hongyi Jiang, Deyuan Liu, Shaolin Tan

Journal of System Simulation

Abstract: Modeling and simulation of complex systems are critical issues for understanding their structural and functional properties. The ability of graph neural networks (GNNs) to learn and represent the internal correlations within data provides a new approach for modeling and simulating complex systems. Currently, there are various types of GNN models involving frequency-domain, spatial-domain, generative, heterogeneous, and spatio-temporal models. These models are widely applied in complex system modeling and simulation research in multiple fields such as industrial internet, social networks, and supply chains based on specific tasks and scenarios. Starting from three representative tasks: network topology representation, dynamic evolution modeling, …

Intelligent Transition Of Automotive Industry Driven By Autonomous Driving Simulation Testing Technology, Jianping Wu, Guanzhou Li, Shuai Zhao, Ling Huang

Journal of System Simulation

Abstract: As a pivotal approach supporting the safety verification and commercial implementation of intelligent driving systems, autonomous driving simulation testing has achieved remarkable progress in technical methodologies and application scenarios. Conventional real-world road testing faces critical limitations including prohibitive costs, inadequate coverage of corner case scenarios, and efficiency bottlenecks, rendering it insufficient for safety validation of high-level autonomous driving systems (L4 and above). To address these challenges, simulation testing frameworks have evolved into a multi-layered verification system encompassing mathematical modeling, virtual scenarios, hardware-in-the-loop (HIL), mixed reality, and cloud-based simulation clusters. Specifically, mathematical modeling accelerates algorithm development; virtual scenario simulation enhances …

Digital Twinned Industrial Robot: Conceptual Framework, Key Technologies, And Case Study, Yongkui Liu, Kang Yang, Benben Tuo, Yaduo Pan, Xinyu Wang, Yihan Wang, Yongqian Gong, Lin Zhang, Lihui Wang, Tingyu Lin, Bin Zi, Yuan Li, Wei You, Xun Xu

Journal of System Simulation

Abstract: To effectively enhance the value and full life cycle management level of industrial robots, this paper integrated deeply digital twin with industrial robots and discussed a new concept, namely digital twinned industrial robot (DTIR). It defined the concept, composition, and typical characteristics of DTIRs and proposed their system architecture. From the perspective of the full life cycle of "design, manufacturing, operation and maintenance, and decommissioning", the key technologies of DTIRs were systematically sorted out. Furthermore, the validity of the proposed conceptual framework was verified through a case study. Finally, the paper summarized the findings and discussed the future development …

Large-Scale Social Simulator: Frontiers And Perspectives, Jinghua Piao, Chen Gao, Fang Zhang, Jun Su, Yong Li

Journal of System Simulation

Abstract: Social experiments, as a typical research method in social sciences, aim to study specific social phenomena or the impacts of policies by observing the behaviors of individuals, organizations, or social groups in real or simulated environments. However, traditional social experiment methods often face challenges such as random bias, high costs, and ethical risks, making them inadequate to address increasingly complex research demands. Against this backdrop, computational social experiments have emerged, enabling researchers to conduct social experiments within computational simulation environments that are free from random bias, cost-efficient, and ethically manageable. Meanwhile, China is currently undergoing a critical period of …

What Drives Weight Status Among Female University Students? A Machine Learning Analysis Of Sociodemographic, Dietary, And Lifestyle Determinants, Radwan Qasrawi, Abir Ajab, Leila Cheikh Ismail, Ayesha Al Dhaheri, Sharifa Alblooshi, Razan Abu Ghoush, Stephanny Vicuna Polo, Malak Amro, Suliman Thwib, Ghada Issa, Haleama Al Sabbah

All Works

Background: Obesity and underweight are increasingly common among young adult women, often resulting from complex interactions between diet, lifestyle, and socioeconomic factors. This study addresses that gap by applying machine learning to a wide range of behavioral, dietary, and demographic data. The main research question asks: What are the key factors influencing weight status among female university students, and how accurately can machine learning models identify them? We hypothesize that different factors are significantly associated with underweight, overweight, and obesity, and that machine learning can reliably detect these patterns. The aim is to identify the strongest predictors and support more …

Stranger Disputes: When Artificial Intelligence Turns Arbitration Upside Down, Imre Stephen Szalai

Pepperdine Dispute Resolution Law Journal

Arbitration agreements are everywhere in the United States. These agreements already block access to courts in a troubling manner, and pursuant to these agreements, parties must resolve their disputes before a private, human arbitrator with broad, virtually unreviewable powers. However, with the growth of AI, companies could easily redraft their contracts to require arbitration before non-human bots or AI arbitrators instead of a human arbitrator. Based on the history, values, policy, and text of the Federal Arbitration Act (FAA), this Article concludes that the FAA would govern and support the use of an AI arbitrator. As a result, a pre-dispute …

Detecting Android Malware Based On Static Analysis Using Classification And Modified Clustering Techniques, Abdullah Allawi Al-Sraratee, Ahmed Habeeb Al-Azawei

Journal of Intelligent Informatics, Networking, and Cybersecurity

Because Android malware harms internet security, prior research proposes several different approaches to detect it accurately. However, such proposed models depend on numerous number of features to attain high accuracy. This could lead to high computation cost and potential overfitting. Furthermore, manual data labeling is labor-intensive, requiring significant human effort and skills. This research aims to: 1) extend previous literature on Android malware detection, 2) improve the accuracy of Android malware detection based on a low number of features, and 3) modify a clustering technique to group data into two different clusters to address the issue of unlabeled data. To …

Limitations Of Using Large Language Models For Automated Essay Scoring, Thomas A. Fink

Theses

Background: Automated essay scoring (AES) is a challenging deep learning problem. The two most widely used methods for predicting essay quality scores, supervised learning-based and LLM-based, have their own limitations. Although supervised learning-based methods are more accurate, they only predict a score and do not offer descriptive feedback to students. On the other hand, LLM-based methods can offer rubric-guided feedback but are known to be less accurate.

Methods: This work focuses on improving the accuracy of state-of-the-art LLM-based AES methods. We began by thoroughly investigating why these methods were performing poorly for certain datasets and certain examples. This led us …

Predicting Sleep And Sleep Stage In Children Using Actigraphy And Heartrate Via A Long Short-Term Memory Deep Learning Algorithm: A Performance Evaluation, Robert Weaver Med, Phd, James White, Olivia Finnegan, Hongpeng Yang, Zifei Zhong, Keagan Kiely, Catherine Jones, Yan Tong, Srihari Nelakuditi, Rahul Ghosal, David E. Brown, Russell R. Pate Ph.D., Gregory J. Welk, Massimiliano De Zambotti, Yuan Wang, Sarah Burkart, Elizabeth L. Adams Phd, Bridget Armstrong, Michael Beets Med, Mph, Phd

Faculty Publications

Children's ambulatory sleep is commonly measured via actigraphy. However, traditional actigraphy measured sleep (e.g., Sadeh algorithm) struggles to predict wake (i.e., specificity, values typically < 70) and cannot predict sleep stages. Long short-term memory (LSTM) is a machine learning algorithm that may address these deficiencies. This study evaluated the agreement of LSTM sleep estimates from actigraphy and heartrate (HR) data with polysomnography (PSG). Children (N = 238, 5–12 years,52.8% male, 50% Black 31.9% White) participated in an overnight laboratory polysomnography. Participants were referred be-cause of suspected sleep disruptions. Children wore an ActiGraph GT9X accelerometer and two of three consumer wearables(i.e., Apple Watch Series 7, Fitbit Sense, Garmin Vivoactive 4) on their non-dominant wrist during the polysomnogram. LSTM estimated sleep versus wake and sleep stage (wake, not-REM, REM) using raw actigraphy and HR data for each 30-s epoch. Logistic regression and random forest were also estimated as a benchmark for performance with which to compare the LSTM results. A 10-fold cross-validation technique was employed, and confusion matrices were constructed. Sensitivity and specificity were calculated to assess the agreement between research-grade and consumer wearables with the criterion polysomnography. For sleep versus wake classification, LSTM outperformed logistic regression and random forest with accuracy ranging from 94.1to 95.1, sensitivity ranging from 94.9 to 95.9 across different devices, and specificity ranging from 84.5 to 89.6. The addition of HR improved the prediction of sleep stages but not binary sleep versus wake. LSTM is promising for predicting sleep and sleep staging from actigraphy data, and HR may improve sleep stage prediction.

Perceptions Of Blind Adults On Non-Visual Mobile Text Entry, Dylan Gaines, Keith Vertanen

Michigan Tech Publications

Text input on mobile devices without physical keys can be challenging for people who are blind or low-vision. We interview 12 blind adults about their experiences with current mobile text input to provide insights into what sorts of interface improvements may be the most beneficial. We identify three primary themes that were experiences or opinions shared by participants: the poor accuracy of dictation, difficulty entering text in noisy environments, and difficulty correcting errors in entered text. We also discuss an experimental non-visual text input method with each participant to solicit opinions on the method and probe their willingness to learn …

Identifying The Desired Word Suggestion In Simultaneous Audio, Dylan Gaines, Keith Vertanen

Michigan Tech Publications

We explore a method for presenting word suggestions for non-visual text input using simultaneous voices. We conduct two perceptual studies and investigate the impact of different presentations of voices on a user's ability to detect which voice, if any, spoke their desired word. Our sets of words simulated the word suggestions of a predictive keyboard during real-world text input. We find that when voices are simultaneous, user accuracy decreases significantly with each added word suggestion. However, adding a slight 0.15 s delay between the start of each subsequent word allows two simultaneous words to be presented with no significant decrease …

Using Confidence Scores To Improve Eyes-Free Detection Of Speech Recognition Errors, Sadia Nowrin, Keith Vertanen

Michigan Tech Publications

Conversational systems rely heavily on speech recognition to interpret and respond to user commands and queries. Despite progress on speech recognition accuracy, errors may still sometimes occur and can significantly affect the end-user utility of such systems. While visual feedback can help detect errors, it may not always be practical, especially for people who are blind or low-vision. In this study, we investigate ways to improve error detection by manipulating the audio output of the transcribed text based on the recognizer's confidence level in its result. Our findings show that selectively slowing down the audio when the recognizer exhibited uncertainty …

Synthesis Of Cancrinite Zeolite From Toraja Natural Bentonite For Heavy Metal Removal From Wastewater, Yuli Astuti, Paulina Taba, Siti Fauziah, Syarifuddin Liong, Yusafir Hala, Nur Umriani Permatasari, Satria Putra Jaya Negara, Fadliah Fadliah

Karbala International Journal of Modern Science

This study explores the production of cancrinite (CAN) zeolite from bentonite found in Toraja (a place in South Sulawesi Province, Indonesia) and its effectiveness in removing Pb²⁺ and Fe³⁺ ions from wastewater. The synthesis was carried out using a hydrothermal method with varying NaOH concentrations, where a single phase of zeolite was formed at 5 M, as confirmed through XRD analysis. FTIR results showed the characteristics of CAN zeolite with typical absorption peaks at 676, 622, and 565 cm^-1, as well as the presence of carbonate groups (CO₃^2-) at 1300-1400 cm^-1. SEM …

Machine Learning Crime Prediction Models And The Gap Between Research And Implementation: A Systematic Review, Ricardo Huamantingo, Miguel Cano-Lengua, Ciro Rodriguez

Karbala International Journal of Modern Science

A crime is an illegal or violent act committed by one individual against another. The increasing crime rate has become a major concern as it negatively affects people's quality of life and generates significant social and economic costs. This study aims to identify the most widely used machine learning (ML) models for crime prediction, determine evaluation metrics for assessing model performance, and analyze key data characteristics to enhance real-world implementation. The study follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology. A search string was formulated using the population, intervention, comparison, and outcomes (PICO) framework and applied …

Psilostachyin B As Potential Immune Checkpoint Inhibitor Targeting Ctla-4 And Pd-L1 In The Development Of Cancer Immunotherapy: A Computational Investigation, Moh Dliyauddin, Nabila Shafa Yumna Salsabila, Noviana Dwi Lestari, Sapti Puspitarini, Mansur Ibrahim, Sri Rahayu, Muhammad Sasmito Djati, Muhaimin Rifa’I

Karbala International Journal of Modern Science

Immunotherapy is a promising treatment approach by targeting immune checkpoints such as CTLA-4 and PD-L1 to overcome cancer progression. The utilization of Curcuma longa and Phyllanthus niruri as potential immune checkpoint inhibitors offers an alternative cancer therapy. Computational analyses including molecular docking and molecular dynamics with validation using Molecular Mechanics/Poisson-Boltzmann Surface Area (MM-PBSA), Dynamic Cross-Correlation Matrix (DCCM), and Principal Component Analysis (PCA), were performed in this study. Results show that Psilostachyin B is the most promising inhibitor candidate against CTLA-4 and PD-L1, with binding affinity values of -6.9 and -6.8 kcal/mol, respectively. Molecular dynamics simulation results indicated that Psilostachyin B …

"...Anything My Friend Shares, I Would Want To Support Them By Clicking On It": Co-Designing Story-Based Interventions Against Clickbait For Teenagers, Ankit Shrestha, Audrey Flood, Bryson Hackler, Mahdi Nasrullah Al-Ameen

Computer Science Student Research

Teenagers' lack of digital sophistication and cyber hygiene makes them vulnerable to social engineering attacks, especially as they start using social media. Clickbait, one of such attacks, is primarily performed through social media to trick users into clicking on malicious links. With teenagers' increasing use of social media, clickbait poses a substantial threat to their online safety. The existing online safety measures for teens mainly focus on parental mediation, which can be perceived as restrictive and privacy-invasive. To this end, researchers recommended empowering teens to deal with online risks. In order to design such interventions for clickbait, we conducted co-design …

Digital Forensics And Ai: Artifact Analysis And Using Ai In The Forensics Domain, Clinton Joel Walker

LSU Doctoral Dissertations

Digital Forensics (DF) is a field of forensic science focusing on the acquisition, authentication, and analysis of digital evidence while maintaining integrity of that data. DF analysts use forensic tools to parse large volumes of data for investigations and depend on them for identification of pertinent digital evidence in vast amounts of data. Keeping up with innovations and ever-expanding data volumes is a constant challenge for these investigators. The prevalence of Artificial Intelligence (AI) in everyday computing is rapidly expanding, with the use of Machine Learning (ML) and Large Language Models (LLM)s becoming increasingly commonplace. Innovations in technology bring new …

Research And Education In Robotics: A Comprehensive Review, Trends, Challenges, And Future Directions, Mutaz Ryalat, Natheer Almtireen, Ghaith Al-Refai, Hisham Elmoaqet, Nathir Rawashdeh

Michigan Tech Publications

Robotics has emerged as a transformative discipline at the intersection of the engineering, computer science, and cognitive sciences. This state-of-the-art review explores the current trends, methodologies, and challenges in both robotics research and education. This paper presents a comprehensive review of the evolution of robotics, tracing its development from early automation to intelligent, autonomous systems. Key enabling technologies, such as Artificial Intelligence (AI), soft robotics, the Internet of Things (IoT), and swarm intelligence, are examined along with real-world applications in healthcare, manufacturing, agriculture, and sustainable smart cities. A central focus is placed on robotics education, where hands-on, interdisciplinary learning is …

Review Of Averting The Digital Dark Age: The Future Of Digital Literary Heritage, Rebecca L. Hastings

Journal of Contemporary Archival Studies

In Averting the Digital Dark Age: How Archivists, Librarians, and Technologists Built the Web a Memory, Ian Milligan explores the efforts of technologists and information professionals to develop means of preserving information shared on the World Wide Web. The web lacks a built-in archiving function, raising fears of a “digital dark age,” an unprecedented gap in the historical record as information sharing via the web increases. Milligan tracks the development of web preservation debates and activities from the anxiety and turmoil of the early to mid-1990s to the coming of age of web preservation in the wake of the …

Integrating Artificial Intelligence And Machine Learning Technologies Into Common Operating Picture And Course Of Action Development, C. Anthony Pfaff, Christopher John Hickey

Books, Monographs & Collaborative Studies

C. Anthony Pfaff and Christopher John Hickey, Principal Investigators

©2025 C. Anthony Pfaff. All rights reserved.

Integrating Artificial Intelligence and Machine Learning Technologies into Common Operating Picture and Course of Action Development explores the potential of artificial intelligence (AI) and machine learning to revolutionize military planning processes by enhancing situational awareness and expediting course of action development within the Joint planning process. The study delves into technical, organizational, and resource considerations that are critical for AI integration. In addition, the study highlights the importance of clean, structured data in training AI systems, addresses challenges in data collection across varying formats …

Using Linear Programming And Game Theory To Optimize The Relation Between Us And China, Junhao Su

Student Works

This paper develops an optimization model to analyze U.S.–China bilateral trade dynamics and competition in artificial intelligence (AI). First, grounded in WTO tariff limits, we formulate a linear programming model to maximize the combined trade volume and conduct a comprehensive sensitivity analysis on tariff parameters. Second, we integrate zero‑sum and non‑zero‑sum game‑theoretic frameworks to identify the Nash equilibria governing both trade negotiations and technological rivalry. The model is implemented in Python using PuLP and is empirically validated with real‑world tariff data to highlight the policy relevance of the optimal solutions. Our results reveal a high concordance between the zero‑sum game …

Seeking Structure In Complex Systems: From Feature Analysis To Space-Time Causal Discovery With Earth Science Applications, Jeffrey J. Nichol

Computer Science ETDs

Complex systems are difficult to study because of their many interacting parts, emergent phenomena, and feedback loops. These systems underpin all life on Earth. We need improved tools for seeking an understanding of them. This body of research presents my investigations into data-driven methods for understanding complex systems, including my invention of a novel causal discovery meta-algorithm for space-time gridded data. I demonstrated machine learning feature importance and causal discovery capabilities for comparing simulated and observed climate data. I developed a new benchmark for modeling space-time dynamics of locally driven phenomena and examined a prominent causal discovery algorithm. Finding that …

"Chatgpt Told Me To Say It": Ai Chatbots And Class Participation Apprehension In University Students, Daisuke Akiba

Publications and Research

The growing prevalence of AI chatbots in everyday life has prompted educators to explore their potential applications in promoting student success, including support for classroom engagement and communication. This exploratory study emerged from semester-long observations of class participation apprehensions in an introductory educational psychology course, examining how chatbots might scaffold students toward active and independent classroom contribution. Four students experiencing situational participation anxiety voluntarily participated in a pilot intervention using AI chatbots as virtual peer partners. Following comprehensive training in AI use and prompt design given to the entire class, participants employed systematic consultation frameworks for managing classroom discourse trepidations. …

Creativity And Curb Cuts: Experiences In Our First Offering Of A Front End Development And Accessibility Focused Cs Course, Briana C. Bettin, Tony Garnett, Alex Gore, Andrea Llanas

Michigan Tech Publications

Students learn an abundance of technical skills while obtaining a computer science degree. The ability to develop meaningful front end user interfaces is often considered the domain of only ''more artistic'' CS students. However, for users to effectively engage with any piece of software, functional user interfaces are critical. Moreover, even among students who have front end skills, semantic and accessible design is all too often less considered. The first author piloted a ''Front End Development and Accessibility'' course this past Fall. This course teaches basic skills of front end with web and leverages key accessibility standards via WCAG. This …

Qder: Query-Specific Document And Entity Representations For Multi-Vector Document Re-Ranking, Shubham Chatterjee, Jeff Dalton

Computer Science Faculty Research & Creative Works

Neural IR has advanced through two distinct paths: entity-oriented approaches leveraging knowledge graphs and multi-vector models capturing fine-grained semantics. We introduce QDER, a neural re-ranking model that unifies these approaches by integrating knowledge graph semantics into a multi-vector model. QDER's key innovation lies in its modeling of query-document relationships: rather than computing similarity scores on aggregated embeddings, we maintain individual token and entity representations throughout the ranking process, performing aggregation only at the final scoring stage-an approach we call "late aggregation." We first transform these fine-grained representations through learned attention patterns, then apply carefully chosen mathematical operations for precise matches. …

Understanding The Roots Of Swarm Intelligence In Defence To Find The Path Forward: A Scientometric Study Of Autonomous Systems, Anton Klarin, Pi-Shen Seet, Janice Jones, Michael N. Johnstone, Helen Cripps, Jalleh Sharafizad, Tony Marceddo

Research outputs 2022 to 2026

Swarm intelligence, inspired by the decentralised, adaptive and self-synchronising behaviours of natural swarms, is a pivotal component of autonomous systems, enhancing efficiency, robustness and scalability. The research in this area is nascent and interdisciplinary. To drive this important research forward, it is necessary to adopt a systems perspective on what is available in the current literature. This chapter offers a comprehensive systems perspective of the integration of swarm intelligence within the broader domain of automation, emphasising its application in the defence sector. A systems perspective of an interdisciplinary field is afforded through scientometrics. Using VOSviewer algorithms, we analysed 1706 publications …

Role Of Staphylococcus Aureus And Streptococcus Pyogenes Biofilms On The Alternation Of Cellular Immunity In Pediat-Ric Tonsillitis Patients, Shayma Ali Hussein, Taban Kamal Rasheed

Karbala International Journal of Modern Science

This study examines the effect of Staphylococcus aureus and Streptococcus pyogenes biofilms on cellular hematological parameters and distribution and phenotyping of cellular immunity in mucosal tissue of tonsils. Thirty healthy controls and fifty pediatric tonsillitis patients participated in the research. Thirty isolated S. aureus and S. pyogenes were tested for biofilm-forming capability (BFC). Hematological parameters were assessed before tonsillectomy, and 9 tonsil samples were evaluated using hematoxylin and eosin stain to investigate the histopathological alterations. Immunohistochemistry (IHC) staining was carried out for detecting dendritic cells (CD1a), neutrophils (CD15), macrophages (CD68), helper T cells (CD4), and cytotoxic T cells (CD8). Hematological …

Neurophysiology And Endocrine Responses To Hunger And Satiety Mechanisms: The Brain-Gut Crosstalk, Nour Shakir Rezaieg, Muthanna M. Awad

Karbala International Journal of Modern Science

Background: Obesity is a main public health problem which substantially increases the risk of many diseases. The complex neural circuitry controls energy homeostasis and food consumption by the incorporation of hormonal and neural signals. Circulating hormones, in specific the gut hormones, have been found to be very important in appetite regulation. These hormones transfer energy situation signs to the brain throughout three principle paths: the circulation system, activation of the vagus nerve, and direct modification of main brain regions such as the hypothalamus and brainstem. The control of food eating is not exclusively dependent on the homeostatic processes, rather it …

A Novel Chaotic Dna-Based Image Cryptosystem Leveraging Euclidean Division, Dynamic Josephus Traversal, And Reservoir Computing, Ahmed Kareem Shibeeb, Salah Albermany, Sadiq A. Mehdi

Karbala International Journal of Modern Science

This study presents a new chaotic DNA-based image cryptosystem that combines Euclidean division, dynamic Josephus traversal (DJT), and reservoir computing to address the weaknesses of current methods. Old chaotic DNA cryptosystems usually have problems such as using the same keys for different messages, simple DNA processes, and being vulnerable to attacks where the attacker can choose the input or try many options. The cryptosystem in this study uses a 7D hyperchaotic system that starts with keys created from SHA-512 hashes to produce changing keystreams based on the plaintext, making it very strong against such attacks. The proposed cryptosystem uses a …

Location Selection Of Migrating Beetles Under Neutrosophic Model With Sensitivity And Comparative Analysis, Rabih Sbera, Ahmed A El-Douh, Darin Shafek, Tareef S. Alkellezli

Neutrosophic Systems with Applications

Location Selection of Migrating Beetles has different criteria to select the best location. So, multi-criteria decision making (MCDM) is used to deal with different and numerous criteria in this study. This study proposes an MCDM methodology to rank the locations and select the best criterion. The average method is used to compute the criteria weights. The locations are ranked using the root assessment method (RAM). This study uses eight criteria and 20 locations. We use the single valued neutrosophic numbers (SVNNs) to overcome uncertainty and vague information. The RAM methodology is used under the SVNNs. The results show that Availability …