Computer Sciences Commons^™

City Regional Traffic Flow Prediction Based On Spatiotemporal Multi-View Attention Residual Network, Jing Chen, Guowei Yang, Zhaochong Zhang, Wei Wang

Journal of System Simulation

Abstract: However, efficiently and comprehensively capturing the complex spatiotemporal correlations within urban traffic flow presents a key challenge. Existing research methods struggle to fully capture these spatiotemporal dependencies. To address these issues, we propose a novel end-to-end deep learning framework called the spatiotemporal multi-view attention residual network (ST-MVAR) for predicting traffic flow in urban areas. we integrate the proximity, periodicity, trend, and external factors of traffic flow as inputs to the network. This network employs skip connections to form a multi-layer nested residual network structure. Additionally, we design a Multi-View Extension module to capture spatial dependencies of traffic flow at …

Economic Optimal Scheduling Of Microgrid Considering Elastic Recovery, Jianghong Chen, Kanghao Shi, Jiahui Hu, Xiaohan Zhao

Journal of System Simulation

Abstract: To enhance the ability of microgrids (MGs) to withstand extreme disaster events, this paper proposes a multi-objective scheduling model considering resilience restoration and economic performance, based on the traditional concepts of power system resilience and reliability. Resilience is specifically quantified. The model integrates energy storage into the objective function and includes reliability indicators as constraints, building on traditional microgrid economic dispatch. The optimization problem is solved using an improved white shark optimizer (WSO) and multi-objective fuzzy programming, where different weights are assigned to each objective function, and the optimal weights are determined through case studies. A microgrid scheduling scheme …

Three-Way Decision Clustering Algorithm Fusion Of Mutant Fireflies Algorithm, Zhaobin Li, Jun Ye, Haoyan Zhou, Yixin Wang, Yuzhen Han

Journal of System Simulation

Abstract: To address problems such as the premature phenomenon in the three-way clustering algorithm caused by the random selection of initial cluster centers and the need for repeated experiments to determine the value of q in the q-nearest neighbor concept, a three-way clustering algorithm optimized by a variant of the firefly algorithm is proposed. The firefly algorithm is employed to solve the problem of sensitivity to initial cluster centers. The target function value is taken as the brightness intensity of firefly to search the clustering center point, and the optimal solution is taken as the clustering center of the algorithm …

Tohf: A Feature Extractor For Resource-Constrained Indoor Vslam, Ruoqing Li, Yaochi Zhao, Zhuhua Hu, Wenlu Qi, Guangfeng Liu

Journal of System Simulation

Abstract: To address the issues of sensitivity to texture and lighting variations, excessive local dependence caused by feature point redundancy, and storage overhead under hardware resource constraints in existing VSLAM feature extractors in indoor environments, We propose the Texture- Oriented and Homogenized FAST Feature Extractor (TOHF), which integrates HVS (Human Visual System) for enhanced texture analysis. TOHF employs a two-stage thresholding strategy and dynamically adjusts feature point distribution, balancing computational efficiency and storage needs. We conducted experimental verification based on the ORB-SLAM3 framework on dataset from resource-limited device and the EuRoc dataset, focusing on matching rate, reprojection error, absolute trajectory …

Electric Vehicle Dispatching Strategy And Incentive Evaluation Based On Virtual Energy Storage, Shuo Chen, Hao Hu, Huimin Fang, Haiwei Wang, Xiaolong Chen, Chengcheng Mei, JiaʹNan Zhu, Qian Ai

Journal of System Simulation

Abstract: To address the multifaceted challenges arising from the widespread integration of electric vehicles into the power grid, harnessing the dispatchability features of electric vehicles becomes imperative. This paper based on a virtual energy storage aggregation model, optimizes the charging scheduling of electric vehicles and assesses their charging incentives through a composite weighting methodology. It establishes a framework for the participation of flexible loads in distribution network scheduling, formulates a second-order cone relaxation optimal power flow model, and develops dispatch strategies. By quantifying the contribution of electric vehicles concerning their flexibility and system stability, and simulating user charging preferences using …

Visual Slam Algorithm Based On Feature Point Selection In Dynamic Scenes, Limei Jiang, Xinwei Chen

Journal of System Simulation

Abstract: To address low positioning accuracy and robustness in traditional visual SLAM algorithms under dynamic conditions, this paper proposes an improved dynamic SLAM algorithm based on feature point selection. Built upon the ORB-SLAM3 framework, it incorporates dynamic region partitioning and feature point filtering. The dynamic region partitioning module utilizes an enhanced RT-DETR object detection algorithm to detect dynamic objects in the images and divides the dynamic regions based on the detection boxes. The feature point selection module utilizes epipolar constraints and optical flow methods to filter out feature points on moving objects, retaining stationary dynamic objects and background points within …

Reinforcement Learning Modeling Of Missile Penetration Decision Based On Combat Simulation, Bin Zhang, Yonglin Lei, Qun Li, Yuan Gao, Yong Chen, Jiajun Zhu, Chenlong Bao

Journal of System Simulation

Abstract: Penetration capability is a primary measure of missile systems. In response to the shortcomings of traditional knowledge-based decision-making methods that are difficult to adaptively evolve, an intelligent penetration decision-making based on combat simulation and DRL is proposed. A missile intelligent decision-making training environment is constructed based on the WESS system. Taking missile maneuver penetration decision-making as an example, a maneuver penetration decisionmaking network model is designed and trained based on the SAC-discrete algorithm and the test of intelligence is conducted. Experimental results show that the intelligent decision model derived from machine learning has a better combat outcome than traditional …

Research On Transformer Fault Diagnosis Method Based On Digital Twin, Lun Jiang, Dajiang Wang, Wenlei Sun, Shenghui Bao, Han Liu, Saike Chang

Journal of System Simulation

Abstract: Aiming at the inability of existing intelligent algorithms for transformer fault diagnosis to quickly and efficiently identify transformer faults, resulting in fault misdetection and untimely detection, this paper proposes a transformer fault diagnosis method using the improved sparrow optimization algorithm to optimize the two-layer fault diagnostic model of XGBoost combined with the digital twin technology. The method adopts advanced sensors to collect oil and gas data and temperature data of the transformer, uses 5G module to transmit the real-time data to the digital twin system. The system monitors the temperature data in real-time by setting the equipment alarm threshold; …

Research On Air Target Threat Assessment Technology Based On Deep Learning, Dawei Jiang, Yangyang Dong, Lidong Zhang, Xiao Lu, Chunxi Dong

Journal of System Simulation

Abstract: In order to realize the effective assessment of air combat targets, a deep learning-based air target threat assessment method is proposed. According to threat characteristics of the air target, the threat attributes of air target faced by electronic countermeasure operation are analyzed from the two perspectives of platform layer and equipment layer, the air target threat assessment index system is constructed, and the air target threat assessment index data set is established. Based on convolutional neural network, a residual structure is introduced to optimize the network, a threat assessment model is established, and the threat ranking of air targets …

Multi-Strategy Hybrid Mountain Gazelle Optimizer For Robot Path Planning, Xu Jin, Yuanbin Mo

Journal of System Simulation

Abstract: Aiming at the problems of local optimum and premature convergence in the design of optimization path of robot navigation system, a multi-strategy hybrid MGO(HMGO) improved algorithm based on the mountain gazelle optimizer(MGO) is proposed. The algorithm uses the quasi-reverse learning strategy to optimize the population initialization ensuring its diversity, introduces the dynamic adaptive density factor to adjust the parameters of the optimization mechanism, and integrates arithmetic optimization and sine-cosine strategies for random perturbations. Through ablation experiments, 13 benchmark test functions, and simulation experiments on the solution of two-dimensional and threedimensional space robot path planning problems, the results demonstrate that …

Artificial Intelligence For Better In-Game Nfl Performance, Christopher Mcmanus

Honors Theses

In this thesis I examined the use of AI modeling for the use in the modern-day NFL, both for improving in-game play calling, and creating better recovery plans for players all around the league. When finding articles detailing these models, I only focused on works involving the current day NFL, and models used widely around the league to this day. The literature detailed in this thesis mainly describes modeling used by Amazon Web Services (AWS, 2024, The NFL’s partner for all things analytics, and data modeling. My main objective for this literature review was to show the impact AI modeling …

“Smart Trap”: A Portable Device For Real-Time Mosquito Capturing And Classification Using Image-Based Analysis, Fahim Rahman

USF Tampa Graduate Theses and Dissertations

Capturing mosquitoes in real-time and taking high-quality images for classification with state-of-the-art methods is not only time-consuming but also expensive. Sometimes even carefully controlled environments and experimental setups fail to capture living mosquitoes. Catching live mosquitoes is necessary to be able to study aspects of their physiology and behavior that cannot be investigated by collections of resting mosquitoes and dead specimens, and to help estimate the local population numbers. My thesis introduces a “Smart Trap”, a small portable device that can attract mosquitoes in real-time, capture them, take high-quality images with dual cameras, and store those images in the cloud. …

Examining Intersectional Queer Biases In Large Language Models: A Combined Statistical And Visual-Qualitative Approach For Quantification And Explanation, Huu Duong (Chip) Nguyen

Computer Science Senior Theses

Despite significant advancements in research on (intersectional) social biases in Large Language Models (LLMs), intersectional biases affecting subgroups within the LGBTQ+ community remain critically understudied. Existing bias detection methodologies often prioritize quantification but lack depth in explaining the specific stereotypes/biases that shape evaluation metrics. To address these gaps, this study proposes a combined statistical and visual-qualitative approach to quantify and identify persistent intersectional queer biases in five recent, state-of-the-art LLMs through a downstream story generation task. Findings from analysis uncover substantial evidence of stereotypes that perpetuate harmful, reductive narratives against intersectionally marginalized groups within the LGBTQ+ community. To promote public …

Artificial Intelligence And Communication Technologies In Academia: Faculty Perceptions And The Adoption Of Generative Ai, Aya Shata, Kendall Hartley

Hank Greenspun School of Journalism and Media Studies Faculty Research

Artificial intelligence (AI) is ushering in an era of potential transformation in various fields, especially in educational communication technologies, with tools like ChatGPT and other generative AI (GenAI) applications. This rapid proliferation and adoption of GenAI tools have sparked significant interest and concern among college professors, who are dealing with evolving dynamics in digital communication within the class-room. Yet, the effect and implications of GenAI in education remain understudied. Therefore, this study employs the Technology Acceptance Model (TAM) and the Social Cognitive Theory (SCT) as theoretical frameworks to explore higher education faculty’s perceptions, attitudes, usage, and motivations, as the underlying …

Feature Manifold Transformer For Detection Of Differential Item Functioning: Visual Detection Of Categorical Feature Nonconformity Through Attention-Based Analysis, Derrick A. Cox, Tanvi Banerjee, William L. Romine

Computer Science and Engineering Faculty Publications

Methods for interpreting complex feature interactions in educational assessment data remain a critical challenge, with traditional statistical approaches often creating barriers to accessibility and interpretability. We introduce the Feature Manifold Transformer (FMT), a novel machine learning approach that leverages dimensionality reduction, representation learning, and transformer architectures to visualize and interpret feature relationships in categorical data. Using the Concept Inventory of Natural Selection (CINS) and Concept Assessment of Natural Selection (CANS) datasets as testbeds, we demonstrate the FMT’s ability to capture subtle relationships between student demographics and response patterns. Our methodology enables both global and local pattern analysis, providing interpretable visualizations …

An Efficient Conjunctive Keyword Searchable Encryption For Cloud-Based Iot Systems, Tianqi Peng, Bei Gong, Chong Guo, Akhtar Badshah, Muhammad Waqas, Hisham Alasmary, Sheng Chen

Research outputs 2022 to 2026

Data privacy leakage has always been a critical concern in cloud-based Internet of Things (IoT) systems. Dynamic Symmetric Searchable Encryption (DSSE) with forward and backward privacy aims to address this issue by enabling updates and retrievals of ciphertext on untrusted cloud server while ensuring data privacy. However, previous research on DSSE mostly focused on single keyword search, which limits its practical application in cloud-based IoT systems. Recently, Patranabis (NDSS 2021) [1] proposed a groundbreaking DSSE scheme for conjunctive keyword search. However, this scheme fails to effectively handle deletion operations in certain circumstances, resulting in inaccurate query results. Additionally, the scheme …

Next Arrival And Destination Prediction Via Spatiotemporal Embedding With Urban Geography And Human Mobility Data, Pengjiang Li, Zaitian Wang, Xinhao Zhang, Pengfei Wang, Kunpeng Liu

Computer Science Faculty Publications and Presentations

With the development of transportation networks, countless trajectory data are accumulated, and understanding human mobility from traffic data could be helpful for smart cities, urban computing, and urban planning. Extracting valuable insights from traffic data, such as taxi trajectories, can significantly improve residents’ daily lives. There are many studies on spatiotemporal data mining. As we know, arrival prediction or regional function detection encompasses important tasks for traffic management and urban planning. However, trajectory data are often mutilated because of personal privacy and hardware limitations, i.e., we usually can only obtain partial trajectory information. In this paper, we develop an embedding …

Energy-Aware Clustering Using Intelligent Scheme For Heterogeneous Wireless Sensor Networks, Enaam A. Al-Hussain, Ghaida A. Al-Suhail

Karbala International Journal of Modern Science

Heterogeneous Wireless Sensor Networks (WSNs) involve nodes with varying capabilities, such as different energy levels, sensing ranges, and computational abilities, which enable them to execute different tasks professionally. Clustering techniques play a crucial role in improving energy efficiency and reliability in WSNs. The evolution of cluster based WSNs from homogeneous into heterogeneous techniques allowed the deployment of smart devices capable of performing complex operations in in diverse environments. However, the heterogeneity of nodes necessitates more sophisticated and adaptive algorithms to fully exploit these capabilities. This paper proposes a new protocol, referred to as IT2F-HLEACH, which integrates Interval Type-2 Fuzzy Logic …

Comprehensive Review On The Application Of Bio-Immunoinformatics In The Development Of Highly Ef-Fective New Candidate Vaccines Against Tuberculosis, Ahyar Ahmad, Andriansjah Rukmana, Miski A. Khairinisa, Dian A. E. Pitaloka, Rosana Agus, Rusdina B. Ladju, Tarwadi Ahmad, Astutiati Nurhasanah, Carina C. D. Joe, Muhammad N. Massi, Harningsih Karim, Irda Handayani, Siti Roszilawati Binti Ramli

Karbala International Journal of Modern Science

Tuberculosis (TB) remains a significant public health challenge worldwide. Currently, Bacillus Calmette-Guerin (BCG) is the only vaccine available for TB prophylaxis. However, the efficacy of the BCG vaccine against adult pulmonary TB is considered inconsistent. This condition encourages researchers to look for more effective options, such as subunit vaccines. This condition requires the development of a more effective subunit vaccine to protect active TB in productive and adult ages. There is an urgent need for more effective vaccines, as the Bacillus Calmette-Guérin (BCG) vaccine currently available has inconsistent efficacy and is only partially effective in adults. Bio-immunoinformatics, an interdisciplinary field …

Articulated Robot Path Planning Based On Hybridization Of Adaptive ‎Dimensionality Algorithm And Grey Wolf Optimizer In Dynamic Environments, Noor Kadhim Ayoob‏, Ali Hadi Hasan

Karbala International Journal of Modern Science

A new method was developed to plan a path for a robotic articulated vehicle using the Grey Wolf Optimizer (GWO) ‎and Adaptive ‎Dimensionality (AD)‎. Existing studies in robotics path planning ignore the differences between robots in terms of size and flexibility and allocate a single cell to the robot regardless of the mentioned factors. Since the articulated robotic vehicle is longer than obstacles moving in the environment, this study takes into account vehicle size and flexibility in path planning by adapting the number of cells allocated to the robotic vehicle to contain the vehicle parts while performing different movements. Considering …

On Signifiable Computability: Part Ii: An Axiomatization Of Signifiable Computation And Debugger Theorems, Vladimir A. Kulyukin

Computer Science Faculty and Staff Publications

Signifiable computability aims to separate what is theoretically computable from what is computable through performable processes on computers with finite amounts of memory. Mathematical objects are signifiable in a formalism ℒ on an alphabet 𝒜 if they can be written as spatiotemporally finite texts in ℒ on 𝒜. In a previous article, we formalized the signification and reference of real numbers and showed that data structures representable as multidimensional matrices of discretely finite real numbers are signifiable. In this investigation, we continue to formulate our theory of signifiable computability by offering an axiomatization of signifiable computation on discretely finite real …

Logiclm: Robust Application Of Large Language Models With Logic Programming For Data Analytics, Evgeny Skvortsov, Shayan Mirjafari, Ojaswa Garg, Yilin Xia, Shaun Bowers, Bertram Ludäscher

Computer Science Faculty Scholarship

We present LogicLM, an OLAP-style interactive data analysis system that leverages large language models (LLMs) and is configured using Logica, an enhanced logic programming language with aggregation support that compiles to SQL. LogicLM uses an LLM to translate natural language queries by end users into executable code for automatically generating data visualizations. For each natural-language query, LogicLM provides a verifiable OLAP-based configuration that users can view and modify to help ensure results are reliable and accurate. This configuration, with measures, dimensions, and filters defined as logical predicates, offers a unified and user-friendly approach to naturallanguage data exploration, while keeping end …

Leveraging Large Language Models For Knowledge-Free Weak Supervision In Clinical Natural Language Processing, Enshuo Hsu, Kirk Roberts

Faculty, Staff and Student Publications

The performance of deep learning-based natural language processing systems is based on large amounts of labeled training data which, in the clinical domain, are not easily available or affordable. Weak supervision and in-context learning offer partial solutions to this issue, particularly using large language models (LLMs), but their performance still trails traditional supervised methods with moderate amounts of gold-standard data. In particular, inferencing with LLMs is computationally heavy. We propose an approach leveraging fine-tuning LLMs and weak supervision with virtually no domain knowledge that still achieves consistently dominant performance. Using a prompt-based approach, the LLM is used to generate weakly-labeled …

Artificial Intelligence In Decision-Making: Literature Review, Najm A. Kh. Alhatimi Aleessawi, Leila Djaghrouri

Journal of the Association of Arab Universities for Research in Higher Education مجلة اتحاد الجامعات العربية للبحوث في التعليم العالي

In the fast-changing world of artificial intelligence (AI), the relationship between technology and decision-making has become a central area of study. Over the past five years, numerous papers have been published examining how AI methods are applied to decision-making processes across various industries. This article aims to highlight the key potential of artificial intelligence to enhance decision-making. It does so by systematically reviewing the literature on the role of AI in improving decision-making, particularly studies published between 2020 and 2024. The review consolidates the main findings from articles in renowned databases such as Google Scholar, Scopus, and IEEE Xplore, offering …

Llms In Network Intrusion Detection – A Comprehensive Analysis, Sudharshan Balaji

USF Tampa Graduate Theses and Dissertations

Network Intrusion Detection Systems (NIDS) play a critical role in identifying and mitigating malicious activities within computer networks. With the rapid evolution of natural language processing (NLP), Large Language Models (LLMs) have emerged as transformative tools across various domains. LLMs, such as OpenAI’s GPT series and Meta’s LLaMA models,have demonstrated remarkable performance in tasks like language generation, reasoning, and classification. Their ability to understand and process vast amounts of data has enabled groundbreaking advancements in areas like healthcare, finance, and cybersecurity. Recent trends highlight their potential to handle unstructured data, perform complex reasoning, and adapt to a wide range of …

Unraveling Genetic Links Between Diabetes And Heart Failure-A Machine Learning Approach, Sunakhi Sahoo, Marzieh Ayati

Research Symposium

Background: Diabetic heart failure (DHF) is defined as a chronic and progressive disease which is associated with both diabetes and heart failure (HF). Even though there have been many developments in the knowledge of these diseases, there is still much to learn about the genetic crossovers between the two. In this study, we identified genes that are associated with diabetic heart failure and heart failure by using gene expression data from patients with DHF, HF, and a control group of patients who died of natural causes. We sought to identify genes that had altered expression levels which could possibly play …

Editorial: Machine Learning Advancements In Pharmacology: Transforming Drug Discovery And Healthcare, Moom Rahman Roosan, Ramgopal Mettu

Pharmacy Faculty Articles and Research

"In recent years, the integration of machine learning (ML) into pharmacology has revolutionized how we approach drug discovery, disease modeling, and therapeutic development. By leveraging vast datasets and computational power, ML has enabled researchers to uncover patterns, predict outcomes, and accelerate drug development processes that were previously unimaginable. This Research Topic on 'Machine Learning Advancements in Pharmacology' features five impactful studies that highlight the diverse applications and potential of ML in this field. These contributions, encompassing original research and a systematic review, exemplify the transformative role of ML in addressing some of the most pressing challenges in pharmacology."

Designing Accessible Ui/Ux For Epileptic Patients: A Scalable Solution For Music Therapy Delivery, Amethyst G.H. Mckenzie

Computer Science Senior Theses

How can we design an accessible, scalable UI/UX system tailored to the cognitive, visual, and motor impairments of epileptic patients, that ensures safe and effective interactions with music therapy applications? This research explores the intersection of accessibility, user-centred design, and digital health, using an iterative design process to develop and refine the SONATA app—a clinically deployable music therapy platform.

Through two prototype iterations, usability testing, and quantitative event logging, this study compares the effectiveness of structured versus flexible navigation in improving user experience. Key findings reveal that structured navigation reduces unintended detours, while progressive disclosure techniques enhance instructional clarity. Additionally, …

Ai In Our Library: Some Serious Reflections And A Few Curiosities, Evan Rusch, Nat Gustafson-Sundell

Library Services Publications

At Minnesota State University, Mankato, we’ve undertaken several experiments and initiatives focused on Generative AI. We provided several examples at the Generative AI in Libraries (GAIL) conference and Northern Ohio Technical Services Librarians (NOTSL) Fall General Meeting. This presentation provided a revised and expanded overview of our initiatives for the Creativity in Technical Services Interest Group (CITSIG). We briefly reviewed how we’ve tested Gen AI to improve data visualization for collections outreach. We provided an overview of limitations on how library-licensed resources can be used with AI, including a foray into retrieval augmented generative AI tools such as the Primo …

Model Explanations For Gender And Ethnicity Bias Mitigation In Ai-Generated Narratives, Martha Otisi Dimgba

Dissertations and Theses

Large Language Models (LLMs) are increasingly utilized in diverse applications, ranging from professional content creation to decision-making systems. However, their outputs often amplify the biases present in their training data, perpetuating stereotypes and reinforcing societal inequities, particularly regarding gender and ethnicity. Such biases can cause tangible harm, especially for underrepresented groups, and require awareness and effective mitigation strategies.

This work explores gender and ethnicity representation in narratives created by generative AI describing 25 occupational fields defined by the U.S. Bureau of Labor Statistics. We examine three large language models (LLMs)--Llama 3.1 70B Instruct, Claude 3.5 Sonnet, and GPT 4.0 Turbo. …