Computer Sciences Commons^™

Mixed-Variable Particle Swarm Optimization Algorithm Based On Competitive Coevolution, Hu Zhang, Heng Zhang, Zilu Huang, Zhe Wang, Qingpo Fu, Jin Peng, Feng Wang

Journal of System Simulation

Abstract: For the current algorithm, it is difficult to obtain the available solution due to the irregularity of problem decision space caused by the numerous mixed variable optimization problems during real industrial applications. The coevolution strategy is introduced and a mixed variable particle swarm optimization algorithm(CCPSO) based on competitive coevolution is proposed. The search direction adjustment mechanism based on tolerance is designed to judge the evolution state of particles, adaptively adjust the search direction of particles, avoid falling into local optimum, and balance the convergence and diversity of the population. The learning object generation mechanism is adopted for each particle …

Handling Constrained Multi-Objective Optimization Problems Based On Relationship Between Pareto Fronts, Yubo Wang, Chengyu Hu, Wenyin Gong

Journal of System Simulation

Abstract: To address the challenges of balancing the constraint satisfaction and objective function optimization, and dealing with the complex feasible regions in constrained multi-objective optimization problems(CMOPs), a classification-based search approach is proposed based on different Pareto front relationships. A dual-population dual-phase framework is proposed in which an auxiliary population Pa and a main population Pm are evolved and the evolution process is divided into a learning phase and a search phase. During the learning phase, Pa explores unconstrained Pareto front (UPF) and Pm explores constrained Pareto front(CPF), through which the relationship between UPF and CPF is determined. After completing the …

Element Grouping Faceted Fully Connected Network Based On Ris, Shunhu Hou, Shengliang Fang, Qingyao Zeng, Mengtao Wang

Journal of System Simulation

Abstract: In view of the over-fitting problem that caused by multiple parameters and high memory usage of the full connection layer of neural network in training, a RIS-based element grouping areal fully connected neural network (RGFCNN) is proposed for the first time based on the structural characteristics of reconfigurable intelligence surface (RIS). Based on the structural characteristics of RIS, the network is optimized on traditional FCNN. A novel transmission surface attention mechanism is designed for the effective feature extraction of data. Compared with the traditional FCNNs, the proposed network does not arrange the data in one-dimensional manner. Instead, a element …

Research On Theoretical Framework Of Simulative Experiment Evalution For Intelligent Unmanned Swarm Cooperation, Jipeng Wang, Xing Zhang, Hao Wu, Yu Gu, Huijie Yang

Journal of System Simulation

Abstract: As a typical representative of intelligent equipment, the technology, equipment and combat applications of intelligent unmanned swarm are being promoted globally. However, the research on experimental theory of unmanned swarm lags behind the technology and equipment in general. The emergence of swarm ability and complexity of confrontation of unmanned swarm, the nonrepeatability and non-generalization of swam experiment take great challenge to the basic theory and methods of unmanned swarm. The four experimental models including intelligent technology, intelligent equipment, intelligent swarm, and intelligent sos(system of systems) experiment from the perspective of system engineering and the whole life cycle of equipment …

Research On Dynamic Scene Slam Based On Improved Object Detection, Lanxi Shi, Wenxu Yan, Hongyu Ni, Feng Zhao

Journal of System Simulation

Abstract: Aiming at the epipolar constraint matching problem of monocular SLAM in dynamic scenes a dynamic feature point selection method based on object detection is proposed, in which the dynamic feature points in the front-end image frame of SLAM system is eliminated during feature extraction to improve the localization accuracy of SLAM. An improved target detection network is proposed to construct a loss function to describe the bounding box by using the overlap area, distance similarity and cosine similarity, which can achieve the accurate localization of target objects and obtain the range of object feature points in the current image …

Study On Forest Fire Visual Analysis Method For Extinguishing Command In Virtual Environment, Benrun Zhang, Weiqun Cao

Journal of System Simulation

Abstract: Aiming at the demand of forest fire fighting command, the information required for the command, such as geographical environment, meteorological conditions, forest resources and forest fire behavior are comprehensively analyzed, and the data visualization visual analysis method in the virtual forest fire environment is designed and realized. Wang Zhengfei-3D mixed cellular automata model is used to simulate the process of forest fire spread and the difference time method is adopted to predict the forest fire spreading behavior. The change of environmental data in different interest domains is captured in real time, and the multi-view panel and overlay layers are …

Asl-Catboost Method For Wind Turbine Fault Detection Integrated With Digital Twin, Hongtao Liang, Lingchao Kong, Guozhu Liu, Wenxuan Dong, Xiangyi Liu

Journal of System Simulation

Abstract: In view of the low visibility of the current wind farm status monitoring and insufficient realtime operation and maintenance, based on the concept of digital twin five-dimensional model, the framework of wind farm digital twin five-dimensional model is constructed. Aiming at the insufficient fault detection capability of traditional algorithms and unbalanced positive and negative samples in fan fault data set, the improved ASL-CatBoost algorithm is proposed to achieve the accurate detection of fan fault status. Based on the digital twinning platform, combined with MATLAB/Simulink, the simulation mathematical model of doubly-fed wind turbine under the condition of blade mass imbalance …

Using Ai Chatbots As Ideation Machines, Brett Hawley, Naomi Hollans

Student Works

The team analyzed 3 popular chatbots and found that none of them could consistently produce idea-centered essay help responses. The team approached them with 3 separate prompts, one from each of three academic subjects. The team analyzed how each chatbot adapted to the addition of personal information from the “student” and to the phrase, “what are some ideas that could help me get started?” The goal with each interaction was to receive a response in which the chatbot did not produce any pre-written content. Overall, the team’s research did not suggest that AI is fully reliable as an ideation tool.

Hgs-3 The Influence Of A Tandem Cycling Program In The Community On Physical And Functional Health, Therapeutic Bonds, And Quality Of Life For Individuals And Care Partners Coping With Parkinson’S Disease, Leila Djerdjour, Jennifer L. Trilk

SC Upstate Research Symposium

Purpose Statement: Several studies have shown that aerobic exercise can have a positive impact on alleviating symptoms experienced by individuals with Parkinson's disease (PD). Despite this evidence, the potential benefits of exercise for both PD patients and their care partners (PD dyad) remain unexplored. This research project investigates the effectiveness, therapeutic collaborations, and physical outcomes of a virtual reality (VR) tandem cycling program specifically designed for PD dyads.

Methods: Following approval from the Prisma Health Institutional Review Board, individuals with PD were identified and screened by clinical neurologists. The pre-testing measures for PD dyads (N=9) included emotional and cognitive status …

Comprehensive Question And Answer Generation With Llama 2, Matous Hybl

MS in Computer Science Theses

Since the introduction of transformers, large language models have proven capable in many natural language processing fields. However, existing systems still face challenges in generating high-quality extractive questions. Base models and public chatbots fall short if the question source or quantity are critical. Our contribution is a question and answer generator for generating comprehensive, extractive questions and answers. This approach includes fine-tuning a LLaMA 2 base model for answer extraction (AE) and question generation (QG). We evaluate the resulting system using common automated metrics and a manual evaluation. We find that our system is comparable to the latest research and …

Towards Erasing The Distinction Between The Computational And Syntactic Accounts Of Scientific Theories, Timothy Luft

Theses

One of the main goals of philosophy of science is to give a proper account of scientific theories and their structure. One way that accounts of the structure of scientific theories can be distinguished is by the mathematical or logical structures that they involve. For instance, syntactic accounts of scientific theories hold that theories are axioms in a logical framework, whereas semantic accounts are more liberal in the range of mathematical and logical structures they take as pertinent to the structure of scientific theories. Paul Thagard (1988) offers a computational account of scientific theories, which holds that theories are complex …

What Students Have To Say On Data Privacy For Educational Technology, Stephanie Choi

Cybersecurity Undergraduate Research Showcase

The literature on data privacy in terms of educational technology is a growing area of study. The perspective of educators has been captured extensively. However, the literature on students’ perspectives is missing, which is what we explore in this paper. We use a pragmatic qualitative approach with an experiential lens to capture students’ attitudes towards data privacy in terms of educational technology. We identified preliminary, common themes that appeared in the survey responses. The paper concludes by calling for more research on how students perceive data privacy in terms of educational technology.

A Case Study Of The Crashoverride Malware, Its Effects And Possible Countermeasures, Samuel Rector

Cybersecurity Undergraduate Research Showcase

CRASHOVERRIDE is a modular malware tailor-made for electric grid Industrial Control System (ICS) equipment and was deployed by a group named ELECTRUM in a Ukrainian substation. The malware would launch a protocol exploit to flip breakers and would then wipe the system of ICS files. Finally, it would execute a Denial Of Service (DOS) attack on protective relays. In effect, months of damage and thousands out of power. However, due to oversights the malware only caused a brief power outage. Though the implications of the malware are cause for researching and implementing countermeasures against others to come. The CISA recommends …

Investigating Vulnerabilities In The Bluetooth Host Layer In Linux, Jack Dibari

Cybersecurity Undergraduate Research Showcase

This paper investigates vulnerabilities within the Bluetooth host layer in Linux systems. It examines the Bluetooth protocol's evolution, focusing on its implementation in Linux, particularly through the BlueZ host software. Various vulnerabilities, including BleedingTooth, BLESA, and SweynTooth, are analyzed.

The Security Of Deep Neural Networks, Jalaya Allen

Cybersecurity Undergraduate Research Showcase

Our society has transitioned from our primitive lifestyle to soon, an increasingly automatic one. That idea is further exemplified as we shift into an AI era, better known as Artificial intelligence. Artificial Intelligence is classified as computer systems that can perform tasks that typically require human intelligence. However, a common thought or question that most might have is, how is this done? How does AI process information the way we want it to and have access to so much information? AI is trained by systems called AI models. These modeling programs are trained on data to recognize patterns or make …

High-Resolution And Quality Settings With Latent Consistency Models, Steven Chen, Junrui Zhang, Rui Ning

Cybersecurity Undergraduate Research Showcase

Diffusion Models have become powerful generative models which is capable of synthesizing high-quality images across various domains. This paper explores Stable Diffusion and mostly focuses on Latent Diffusion Models. Latent Consistency Models can enhance the inference with minimal iterations. It demonstrates the performance in image in-painting and class-conditional synthesis tasks. Throughout the experiment different datasets and parameter configurations, the paper highlights the image quality, processing time, and parameter. It also discussed the future directions including adding trigger-based implementation and emotional-based themes to replace the prompt.

Explainability In Multivariate Time Series Classification Machine Learning Models, Emanuel Sanchez, Giovanni Battaglia

23rd Annual A. Paul and Carol C. Schaap Celebration of Undergraduate Research and Creative Activity (2024)

Explainability within models is a crucial part of machine learning (ML) models because it promotes trust in the models by providing insights into how their predictions were determined. Our study applies the classification model XCM's explainability component in identifying the critical features leading to classification decisions on data collected while participants performed patient-handling tasks on manikins. Studies show that nurses sustain musculoskeletal injuries early in their career, attributable to some extent to posture adopted during patienthandling tasks. The ML models classify posture adopted during tasks as "good", "poor", or, in some cases, "neutral", where good posture minimizes the risk of …

Classifying Patient Handling Techniques To Reduce Risk Of Musculoskeletal Injury In Nursing Students, Giovanni Battaglia, Emanuel Sanchez

23rd Annual A. Paul and Carol C. Schaap Celebration of Undergraduate Research and Creative Activity (2024)

Nurses suffer musculoskeletal injuries at a higher proportion than the general population due to physical strain and poor posture during patient-handling tasks; studies show that back injuries occur at a rate of 28.9 cases per 10,000 registered nurses. The purpose of this study is to apply multivariate time series classifiers (MTSCs) to classify six patient-handling tasks and the quality of subject posture (good, poor, or neutral) during these tasks. Manikins weighing 44 lbs, 66 lbs, and 110 lbs simulated patients. In this proof-of-concept study the XCM, ResNet, and MiniRocket MTSCs were trained with data collected from four non-nursing students using …

Citdet, Jordan A. James, Heather K. Manching, Matthew R. Mattia, Kim D. Bowman, Amanda M. Hulse-Kemp, William J. Beksi

Computer Science and Engineering Datasets - Archive

The CitDet dataset is composed of images captured at the USDA Agricultural Research Service Subtropical Insects and Horticulture Research Unit in Fort Pierce, FL, USA. Data was collected between October 2021 and October 2022. 579 images were captured from different sections of the orchard using the open-source application Field Book on Android tablets. While collecting images, we faced the camera in a portrait orientation directly centered on the tree of interest. All images were taken at the edge of the soil in the tree row to simulate a ground-based robot imaging the tree while moving between two rows of trees. …

Mathematically Rigorous Deep Learning Paradigms For Data-Driven Scientific Modeling, Owen Nicholas Davis

Mathematics & Statistics ETDs

This dissertation explores the crucial role of data-driven modeling in science and engineering, with a focus on developing surrogate models to accelerate large-scale computational tasks, aiding in both outer-loop functions like uncertainty quantification and expensive inner-loop tasks within broader computational frameworks. Challenges arise with increased problem dimension and sparse, noisy training data, particularly significant when constructing surrogates for very expensive computational models where acquiring sufficient high-fidelity training data is unfeasible. In such scenarios, training surrogates from an ensemble of multifidelity information sources of varying accuracy and cost becomes essential. We emphasize neural network-based modeling paradigms, which are flexible in integrating …

Immersive Japanese Language Learning Web Application Using Spaced Repetition, Active Recall, And An Artificial Intelligent Conversational Chat Agent Both In Voice And In Text, Marc Butler

MS in Computer Science Project Reports

In the last two decades various human language learning applications, spaced repetition software, online dictionaries, and artificial intelligent chat agents have been developed. However, there is no solution to cohesively combine these technologies into a comprehensive language learning application including skills such as speaking, typing, listening, and reading. Our contribution is to provide an immersive language learning web application to the end user which combines spaced repetition, a study technique used to review information at systematic intervals, and active recall, the process of purposely retrieving information from memory during a review session, with an artificial intelligent conversational chat agent both …

Data Profits Vs. Privacy Rights: Ethical Concerns In Data Commerce, Amiah Armstrong

Cybersecurity Undergraduate Research Showcase

In today’s digital age, the collection and sale of customer data for advertising is gaining a growing number of ethical concerns. The act of amassing extensive datasets encompassing customer preferences, behaviors, and personal information raises questions of its true purpose. It is widely acknowledged that companies track and store their customer’s digital activities under the pretext of benefiting the customer, but at what cost? Are users aware of how much of their data is being collected? Do they understand the trade-off between personalized services and the potential invasion of their privacy? This paper aims to show the advantages and disadvantages …

The Borderline Between Beneficial And Dishonest Ai: A Technical Report, Seth Richards, Katherine Shell, Seth Wright

Student Works

Artificial Intelligence (AI) has been used since 1950 but it was largely overlooked by the public until 2022. Current discussions about AI center around academic integrity. This report seeks to understand if AI can be handled, used, or accepted in Lipscomb’s academic environment as a beneficial aid to writing and research, without actively doing these tasks for an individual. Generative AI is a neural network, which enables it to receive input, gather information from a database of existing content, and create new content [2]. Due to the nature of generative AI, its beneficial contributions to academia are extremely limited.

Individualized Learning As An Ai Tool: A Technical Report, Petsimnan Blessing Dayit, Kasen Holt, Nuala Roper

Student Works

The purpose of the report’s research is to test and analyze whether Artificial Intelligence (AI) platforms can be used as beneficial tools for individualized learning at Lipscomb University without violating the Academic Integrity Policy. The methods section evaluates AI on the scopes of accuracy, analytical thinking, and adaptability. The results demonstrated how each platform responded to the prompts within the lines of the scope. The answers they gave were accurate, detailed, and contained various adaptations to make explanations clearer for the user. The team concluded that AI can be used at Lipscomb as a beneficial tool for students in their …

Artificial Sociality, Simone Natale, Iliana Depounti

Human-Machine Communication

This article proposes the notion of Artificial Sociality to describe communicative AI technologies that create the impression of social behavior. Existing tools that activate Artificial Sociality include, among others, Large Language Models (LLMs) such as ChatGPT, voice assistants, virtual influencers, socialbots and companion chatbots such as Replika. The article highlights three key issues that are likely to shape present and future debates about these technologies, as well as design practices and regulation efforts: the modelling of human sociality that foregrounds it, the problem of deception and the issue of control from the part of the users. Ethical, social and cultural …

Context-Aware Affective Behavior Modeling And Analytics, Md Taufeeq Uddin

USF Tampa Graduate Theses and Dissertations

Affective computing (AC) is a sub-domain of AI that has the potential to assist people by assessing mental states and making appropriate recommendations to patients, loved ones, caregivers, and domain experts. Humans usually produce an enormous amount of data (such as face videos) every day. One of the major challenges for affective computer vision is to efficiently deal with high volumes of data to facilitate automated model development. To cope with this challenge, we developed computer vision algorithms that measure the expressivity of the human face from video data. More precisely, the developed algorithms can map complex affect information from …

Assessing The Promise And Pitfalls Of Chatgpt For Automated Cs1-Driven Code Generation, Fawad Khan, Max Ramsdell

Student Research Symposium

Definition and Overview of Large Language Models:

• Large Language Models (LLMs) are advanced AI algorithms designed to understand, generate, and interact with human language at a vast scale.

The Evolution of LLMs:

• The development of LLMs has progressed
• 1960 - Basic LLM - basic predictive text functions
• 2017- Transformers - Core model powering ChatGPT introduced
• 2022 - ChatGPT context-aware systems

Assessing Chatgpt As A Programming Exercise Generator, Maxwell Ramsdell, Fawad Khan

Student Research Symposium

Motivation

• Proximal Zone of Development
• Teaching Efficiency
• Cross-Discipline Applications

For these to work, we need to evaluate the effectiveness with which chatGPT writes coding exercises

Application Of T Gates For Anti-Concentration In Clifford Circuits, Matthew Dominicis, Mason Toombs, Gabriel Riddle, Parineeta Puja Saha, Himanth Bobba

Undergraduate Research Conference at Missouri S&T

Our study examines the integration of non-Clifford T gates into randomly generated Clifford circuits to enhance their universal unitary capacity. We investigate the impact of T gates on circuit output randomness, focusing on generating random Clifford circuits and analyzing the effects of T gates. Through simulations and analysis, we assess the effectiveness of this modification in achieving outputs consistent with Anti concentration properties while minimizing the required number of Clifford gates. Our findings provide valuable insights into quantum circuits, with implications for quantum computing applications.

A Fisher Information-Based Approach To Improve Labeling Efficiency Of Neural Network Models In Image Classification, Joshua Caruso

Undergraduate Research Conference at Missouri S&T

Active learning is a framework for training machine learning models where the goal is to reduce the number of labels used during training. Neural network models used for image classification require a large training dataset to achieve good accuracy. This project will use active learning to reduce the number of labels needed for training neural network models. We propose to use the Fisher information of the neural network parameters to actively select which images are labelled and included in the training data. A key challenge is the large number of parameters in commonly used neural network models, which significantly increases …