Digital Commons Network^™

An Inference-Centric Approach To Natural Language Processing And Cognitive Modeling, Animesh Nighojkar

USF Tampa Graduate Theses and Dissertations

Reasoning over natural text is highly nuanced, and interpretations can vary widely depending on cultural background, financial status, age, gender, or even mood. This doctoral dissertation seeks to not only mimic human reasoning behaviors but also improve the task used in natural language processing (NLP) to capture naturalistic reasoning, known as the Natural Language Inference (NLI) task. NLI involves determining whether a hypothesis is true (entailment), false (contradiction), or indeterminate (neutral) based on a given premise. Initially, we will investigate the extent to which NLP systems designed to capture semantic equivalence actually measure meaning equivalence. After establishing that they do …

How Do Preservice Teachers Learn To Teach Integrated Computational Thinking?: Evidence From Planning, Enactment, And Reflection, Rachael Dektor, Samuel Severance, Kip Téllez

Journal of Computer Science Integration

This study examines pre-service teachers’ (PSTs) beliefs and understandings about computational thinking (CT) integration and lesson implementation over time. Utilizing a design-based research approach, 3 PSTs led the co-design of integrated CT lessons with support from researchers and enacted these CT integrated lessons with K-5 students. All PSTs participated in a whole-group CT workshop and engaged in one-on-one lesson design sessions with a researcher. We utilized a grounded theory approach to qualitatively analyze pre-surveys, semi-structured interviews, and video data of three PSTs enacting their lessons. We found that PSTs’ initial beliefs about CT instruction – including the importance of it …

Reimagining Web Design: Empowering Agency Of Specialized Audiences Through User-Centered Heuristics, Haley Jones

USF Tampa Graduate Theses and Dissertations

This research seeks to create an alternative model for website design that interrogates standardized, linear ways of knowing and being by placing the audience at the center of the web design process. This research contributed a reimagined approach to traditional and standardized web design heuristics by considering an audience-centric methodology that was practical and applicable for web design praxis to create equitable user experiences which can empower audiences to recall their own knowledge and experience to make meaning for themselves through a reimagining of knowledge-making processes in a network of digitized information. In perceiving the rhetorical choice in design of …

Addressing Social Inequalities Using Ai, Big Data, And Machine Learning, Erica L. Jensen, Lakell Archer, Sumaya Ali

Journal of Nonprofit Innovation

No abstract provided.

Assessment And Prediction Of Meteorological Drought Using Machine Learning Algorithms And Climate Data, Khalid En-Nagre, Mourad Aqnouy, Ayoub Ouarka, Syed Ali Asad Naqvi, Ismail Bouizrou, Jamal Eddine Stitou El Messari, Aqil Tariq, Walid Soufan, Wenzhao Li, Hesham El-Askary

Mathematics, Physics, and Computer Science Faculty Articles and Research

Monitoring drought in semi-arid regions due to climate change is of paramount importance. This study, conducted in Morocco’s Upper Drâa Basin (UDB), analyzed data spanning from 1980 to 2019, focusing on the calculation of drought indices, specifically the Standardized Precipitation Index (SPI) and the Standardized Precipitation Evapotranspiration Index (SPEI) at multiple timescales (1, 3, 9, 12 months). Trends were assessed using statistical methods such as the Mann-Kendall test and the Sen’s Slope estimator. Four significant machine learning (ML) algorithms, including Random Forest, Voting Regressor, AdaBoost Regressor, and K-Nearest Neighbors Regressor, were evaluated to predict the SPEI values for both three …

Improving Flextype: Ambiguous Text Input For Users With Visual Impairments, Dylan Gaines, Keith Vertanen

Michigan Tech Publications

We present an improved version of the FlexType interface for nonvisual text input. FlexType enables nonvisual text input on mobile touchscreen devices by allowing users to select from a small number of character groups with gestures instead of targeting letters at specific screen locations. Based on an interview with users who are blind or low vision, we added a letter-entry mode to enable easier entry of difficult words such as proper nouns. We conducted a longitudinal study with users who are legally blind to compare FlexType to users' typical text input methods. While we found FlexType was significantly slower than …

From Graph Theory For Robust Deep Networks To Graph Learning For Multimodal Cancer Analysis, Asim Waqas

USF Tampa Graduate Theses and Dissertations

This dissertation explores the intersection of graph theory and deep learning, focusing on enhancing the robustness of deep neural networks (DNNs) and applying these advancements to complex problems like cancer diagnosis and treatment. We investigate the structural properties of graphs and their influence on neural network performance, particularly in multimodal learning. The work delves into the design space of DNN architectures using graph-theoretic measures, transforming graphs into DNN architectures for various tasks, and examining their robustness against noise and adversarial attacks. The study extends to medical imaging, highlighting advanced DNN architectures like U-Net for brain tumor segmentation. It addresses the …

Assessing The Impact Of An Rpp On A Large Urban School District: The Case Of Cafécs, Erin Henrick, Danny Schmidt, Steven Mcgee, Andrew M. Rasmussen, Lucia Dettori, Ronald I. Greenberg, Dale Reed, Don Yanek

Computer Science: Faculty Publications and Other Works

This study analyzes the impact of the Chicago Alliance for Equity in Computer Science (CAFÉCS) Research Practice Partnership (RPP) on the Chicago Public School (CPS) Office of Computer Science (OCS). Using a qualitative analysis drawing on data from leadership team meetings, published articles and presentations, and evaluation reports from 11 years of the partnership, we utilized a framework developed by the CAFÉCS leadership team to document the impact on district (1) Programs, (2) Research, (3) Organizational Structures, and (4) Policies leading to (5) Equitable Results for students, condensed as PROSPER. In particular, we explore the role of the RPP in …

Optimizing Cybersecurity Operations Using Data-Driven Intelligence, Jalal Ghadermazi

USF Tampa Graduate Theses and Dissertations

Cybersecurity operations centers (CSOCs) play a crucial role in safeguarding organizations from cyber threats. CSOC operations are divided into two main areas: Intrusion detection systems (IDS) and security response team (SRT) operations. Machine learning (ML) and deep learning (DL) advancements have significantly improved IDSs. IDS can be either flow-based, suitable for offline analysis, or packet-based, which analyze traffic in real-time. However, packet-based IDS often treat packets independently, ignoring the sequential nature of network communication. Additionally, recent ML/DL approaches also struggle with capturing global and structural information and novel attack detection due to their reliance on labeled data. The SRT within …

Transforming Organizational Cyber Security With Artificial Intelligence And Data-Driven Optimization, Soumyadeep Hore

USF Tampa Graduate Theses and Dissertations

This dissertation presents a comprehensive framework for enhancing organizational cybersecurity through data-driven intelligence. The research integrates multiple methodologies to tackle challenges in network intrusion detection and vulnerability management within cybersecurity operations centers (CSOCs). First, the research investigates vulnerability prioritization and mitigation techniques currently employed by CSOCs. To further streamline the vulnerability prioritization and mitigation process a machine learning (ML)-based Vulnerability Priority Scoring System (VPSS) is introduced, significantly improving the prioritization and mitigation of context-sensitive vulnerabilities. The VPSS outperforms traditional methods, reducing the cumulative vulnerability exposure score by up to 30% by considering both organizational context and vulnerability severity. Next, the …

Board 326: K-12 Teachers And Data Science: Learning Interdiscplinary Science Through Research Experiences, Katherine G. Herbert-Berger, Thomas J. Marlowe, Vaibhav Anu, Stefan A. Robila

School of Computing Faculty Scholarship and Creative Works

Data science is now pervasive across STEM, and early exposure and education in its basics will be important for the future workforce, academic programs, and scholarly research in engineering, technology, and the formal and natural sciences, and in fact, across the full spectrum of disciplines. When combined with an emphasis on soft skills and an interdisciplinary focus, such educational experiences have deeper and more meaningful effects. Our Montclair State University NSF Research Experience for Teachers (RET) grant (NSF Award Number: #2206885, IRB Number: 22-23-3003) exposed teachers to a program integrating solar weather, data science, computer science and artificial intelligence, and …

A Robust Data-Driven Framework For Artificial Intelligent Systems, Quoc H. Nguyen

USF Tampa Graduate Theses and Dissertations

Artificial Intelligence (AI) systems have demonstrated remarkable performance across various domains. However, their robustness remains a critical concern, particularly in terms of data and model reliability. This dissertation aims to address the challenges associated with building robust AI systems by focusing on two key aspects: data robustness and model robustness. Data robustness poses significant challenges, including data shift, concept shifting, limited and imbalanced datasets, and interoperability issues in IoT systems for data collection. Existing methods fall short in handling dynamic business objectives and evolving data landscapes effectively. To bridge these gaps, we propose an IoT framework that ensures interoperability, seamless …

Creative Insights Into Motion: Enhancing Human Activity Understanding With 3d Data Visualization And Annotation, Isaac Browen, Hector M. Camarillo-Abad, Franceli L. Cibrian, Trudi Di Qi

Engineering Faculty Articles and Research

This paper presents a novel 3D system for human motion analysis - Motion Data Visualization and Annotation (MoViAn). Designed to provide a comprehensive visual representation of 3D human motion data, MoViAn incorporates detailed visualization of gaze direction, hand movements, and object interactions, alongside an interactive interface for efficient data annotation. A user study involving eight participants indicates that MoViAn enables users to thoroughly explore and annotate human motion data, with System Usability Scale (SUS) results demonstrating a satisfactory usability level. The contribution of this paper lies in the development of an interactive and usable data analytics tool aimed at deepening …

Modified (N + 1) D Laplacian For Smooth Pressure Reconstruction Based On Time-Resolved Velocimetry (1): Analysis And Numerics, Junrong Zhang, Nazmus Sakib, Zhao Pan

Electrical and Computer Engineering Student Research

We analyze a smooth pressure solver based on the ‘modified Poisson equation’: ∇²p + ξ² ∂²p/∂t² = f(u(t)), where p is the pressure field, u(t) is the velocity field measured by time-resolved image velocimetry, and ξ² is a tunable parameter to control the solver’s diffusive behaviour in time. This modified Poisson equation aims at obtaining smooth pressure fields from potentially noisy image velocimetry measurements, and is a part of the current four-dimensional (4D) pressure solver (implemented in, for example, DaVis 10.2) by LaVision. This work focuses on investigating three aspects …

Anonymized Identity Recognition And Classification Using Privacy Preserving Facial Encoding, Manas Sanjay Pakalapati

USF Tampa Graduate Theses and Dissertations

The need for sharing large-scale datasets to train deep neural network models, particularly in healthcare, raises significant data security and privacy concerns. To address these issues, methods such as data encryption or encoding are utilized. These techniques can encrypt the data and make it unreadable to humans, while still retaining its usefulness for training models.

In this study, we investigate various image encoding techniques designed to protect privacy by making images unrecognizable while still retaining their usefulness for model training. Our investigation utilized publicly available facial databases and focused on evaluating the trade-offs inherent in image encoding techniques, with a …

A Simple Mobile Plausibly Deniable System Using Image Steganography And Secure Hardware, Lichen Xia, Jinghui Liao, Niusen Chen, Bo Chen, Weisong Shi

Michigan Tech Publications

Traditional encryption methods cannot defend against coercive attacks in which the adversary captures both the user and the possessed computing device, and forces the user to disclose the decryption keys. Plausibly deniable encryption (PDE) has been designed to defend against this strong coercive attacker. At its core, PDE allows the victim to plausibly deny the very existence of hidden sensitive data and the corresponding decryption keys upon being coerced. Designing an efficient PDE system for a mobile platform, however, is challenging due to various design constraints bound to the mobile systems. Leveraging image steganography and the built-in hardware security feature …

An Empirical Study On Detecting And Explaining Global Structural Change In Evolving Graph Using Martingale, Tarun Teja Kairamkonda

Theses and Dissertations

There is a growing interest in practical applications involving networks of interacting entities such as sensor networks, social networks, urban traffic networks, and power grids, all of which can be represented using evolving graphs. Changes in these evolving graphs can signify shifts in the behavior of interacting entities or alterations in the patterns of their interactions. Identifying and detecting these changes is crucial for addressing potential challenges or opportunities in various domains. In this study, we propose an approach for detecting structure change in evolving graphs based on the martingale change detection framework on multiple graph features extracted over time. …

Integration Of Machine Learning In Structural Health Monitoring For Damage Identification And Response Prediction In Bridges, Naga Lakshmi Chittitalli Ravuri

Theses and Dissertations

Machine learning-based structural health monitoring (ML-SHM) plays a pivotal role in enhancing structural resilience. By recognizing potential hazards, implementing resistance measures, facilitating swift recovery, and continuously monitoring structural health, ML-SHM ensures proactive maintenance and minimizes recovery delays post-events. Leveraging machine learning algorithms and sensor data, ML-SHM enables early detection of anomalies, prediction of failures, and adaptive responses, enhancing the structure's ability to withstand and recover from adverse conditions. This integrated approach not only improves the structure's performance and adaptability but also contributes to overall safety and longevity. This thesis presents a comprehensive exploration of structural health monitoring (SHM) techniques for …

Do You Say Please Or Thank You To Chatgpt? The Subtle Influence Of Prompt Engineering On Digital Civility, Essraa Nawar

Library Articles and Research

"

In the dynamic and rapidly evolving landscape of artificial intelligence, tools like ChatGPT have become integral to our daily digital interactions. These advanced AI systems assist us with a myriad of tasks, from generating text and answering complex questions to providing creative solutions. However, as we engage more frequently with these non-human entities, an intriguing question arises: Are we inadvertently becoming ruder in our digital communications, or are we consciously maintaining our ingrained habits of politeness?"

Accelerated Particle Swarm Optimization Algorithm For Efficient Cluster Head Selection In Wsn, Imtiaz Ahmad, Tariq Hussain, Babar Shah, Altaf Hussain, Iqtidar Ali, Farman Ali

All Works

Numerous wireless networks have emerged that can be used for short communication ranges where the infrastructure-based networks may fail because of their installation and cost. One of them is a sensor network with embedded sensors working as the primary nodes, termed Wireless Sensor Networks (WSNs), in which numerous sensors are connected to at least one Base Station (BS). These sensors gather information from the environment and transmit it to a BS or gathering location. WSNs have several challenges, including throughput, energy usage, and network lifetime concerns. Different strategies have been applied to get over these restrictions. Clustering may, therefore, be …

Large-Scale Research Infrastructure Empowers High-Quality Development Of Private Enterprises: Current Situation, Challenges, And Policy Recommendations, Lingling Zhang, Fuqiang Wang, Mingze Zhang, Zexia Li

Bulletin of Chinese Academy of Sciences (Chinese Version)

Private enterprises have become an important source of innovation in China’s economic development. Large-scale research infrastructure, as a crucial strategic support and innovation element for breaking through key technologies, provides a platform for the innovative development of private enterprises. At present, some large-scale research infrastructures in China, such as the China Spallation Neutron Source and the Shanghai Synchrotron Radiation Facility, have begun actively exploring mechanisms to serve private enterprises. These efforts have helped a number of private companies overcome critical technological bottlenecks and achieve original innovations. Nevertheless, in the current process of opening up large-scale research infrastructures to private enterprises …

Context-Driven: Logic And Pathway Of Industrial Intelligence To Accelerate Development Of New Quality Productive Forces, Ximing Yin, Yaxin Su, Tailun Chen, Jin Chen, Jiang Yu

Bulletin of Chinese Academy of Sciences (Chinese Version)

The development of new productive forces hinges on industrial intelligence, which is driven by the deep integration of technological innovation and industrial innovation, and the accelerated construction of a modern industrial system. Industrial intelligence refers to the process of transforming traditional industrial development models and cultivating new pillar industries through the empowerment of intelligent technologies and data elements. It serves as a pivotal engine for promoting new industrialization and developing new productive forces. However, existing research has largely overlooked the critical theoretical and practical issues of how to leverage China’s ultra-large market and its vast contextual advantages to improve the …

Integration Of Digital And Real Economies To Shape New Advantages In Development: New Form Of Human-Cyber-Physical Ternary Fusion, Jiaofeng Pan, Jing Wu

Bulletin of Chinese Academy of Sciences (Chinese Version)

Facing the accelerating of scientific and technological revolution and industrial transformation, expediting the deep integration of digital economy and real economy is a crucial pathway to enhance industrial competitiveness and address social development challenges. The integration of digital and real economies, with the linkage of human-cyber-physical ternary fusion, brings about an increase in production factors and a reduction in uncertainty. This integration permeates through the whole process and channels of the real economy, including R&D innovation, manufacturing, collaborative integration, and supply services, triggering systemic transformations in the real economy. Looking to the future, the deep connection of technology, data, and …

Digital Technologies Empower Innovative Development Governance Of The Yellow River Basin, Tara Qian Sun, Yingying Jia, Gaozuo Sun, Xixi Zhao, Rongping Mu

Bulletin of Chinese Academy of Sciences (Chinese Version)

The application of digital technologies is the core driving force for innovating traditional development and realizing a leap in productivity. The innovative development governance of the Yellow River Basin is a complex social system, involving economic, social, and ecological aspects. Its key driving force is the profound influence of digital technologies. Focused on how digital technologies empower the innovative development governance of the Yellow River Basin, the development process, problems, and challenges are analyzed at different stages, from the digital Yellow River to the digital twin Yellow River. It is found that the governance of the Yellow River Basin still …

Building Engineering Ecology For Industrial Change In Digital Age, Zhengzhong Xu, Jian Chan

Bulletin of Chinese Academy of Sciences (Chinese Version)

In the digital civilization era, scientific and technological innovation has emerged as a crucial pathway to unleash new quality productive forces and spearhead the ascendancy of great powers. It has become a vital pillar for major nations to engage in international competition and reshape the global order. Furthermore, it acts as a key instrument to smooth out economic cycles and overcome the limitations imposed by these cycles. The rise model, marked by advanced scientific and technological innovation and a commitment to scientific self-sufficiency and enhancement, significantly boosts the viability and acceptance of China’s approach to international governance. At the same …

Study On Data Mining Of Hydrogen Energy Policy In China Based On Natural Language Processing Technology, Dongling Huang, Yuan Liu, Xiaoshuai Yuan, Guozhong Jin, Yuanhang Cai, Li Liu, Heng Cao, Wanjun Li, Rui Cai

Bulletin of Chinese Academy of Sciences (Chinese Version)

Report to the 20th National Congress of the CPC emphasized the importance of “working actively and prudently towards the goals of reaching peak carbon emissions and carbon neutrality”, as well as “speeding up the planning and development of a system for new energy sources”. As a green and low-carbon secondary energy source, hydrogen energy has multiple applications in promoting the large-scale and efficient use of renewable energy as well as energy substitution in the field of transportation. It can also accelerate decarbonization in industry, and as such, is an indispensable part of building a new energy system, reaching peak carbon …

A Pathway For Digital Economy To Enable The Development Of Low-Carbon Transition Under “Technology-Organization-Environment” Framework, Wendong Wei, Yang Sun, Bei Liu, Hui Wang, Yong Geng

Bulletin of Chinese Academy of Sciences (Chinese Version)

The booming development of the digital economy has provided robust technical, management, and institutional means for the in-depth promotion of low-carbon transition. However, at present, there are still problems, such as the limited level of digital technological innovation, the insufficient supply of digital talents, and the urgent need for a sound digital governance system, which constrains the empowering effect of the digital economy on the development of China’s low-carbon transition. Based on the Technology-Organization-Environment (TOE) framework, this study discusses the technology iteration, management transform, and system optimization of the influence of digital economy on the development of low carbon transformation. …

Comparative Analysis And Insights Into R&D Mode Of Top Artificial Intelligence Companies In China And The Us, Xiyi Yang, Jia Jia, Xiaoyu Zhou, Shouyang Wang

Bulletin of Chinese Academy of Sciences (Chinese Version)

Artificial intelligence (AI) is currently one of the most prominent fields in the technology industry, with China and the US being two global centers for AI research and development. However, the two countries differ in their development levels of the AI industry. In particular, the emergence of ChatGPT in 2022 has sparked extensive discussions regarding the capabilities and competitiveness of Chinese AI companies. This study analyzes over 120 000 AI invention patents approved in the past five years in both China and the US. Firstly, it constructs a multidimensional index based on AI patent features to identify the top 10 …

Making Proteomics Accessible: Rokaixplorer For Interactive Analysis Of Phospho-Proteomic Data, Serhan Yılmaz, Filipa Blasco Tavares Pereira Lopes, Daniela Schlatzer, Marzieh Ayati, Mark R. Chance, Mehmet Koyutürk

Computer Science Faculty Publications

We present RokaiXplorer, an intuitive web tool designed to address the scarcity of user-friendly solutions for proteomics and phospho-proteomics data analysis and visualization. RokaiXplorer streamlines data processing, analysis, and visualization through an interactive online interface, making it accessible to researchers without specialized training in proteomics or data science. With its comprehensive suite of modules, RokaiXplorer facilitates phospho-proteomic analysis at the level of phosphosites, proteins, kinases, biological processes, and pathways. The tool offers functionalities such as data normalization, statistical testing, activity inference, pathway enrichment, subgroup analysis, automated report generation, and multiple visualizations, including volcano plots, bar plots, heat maps, and network …

Reinforcement Learning For Robotic Tasks: Analyzing And Understanding The Learning Process Using Explainable Artificial Intelligence Methods, Brian J. Campana

Theses and Dissertations

As deep reinforcement learning (RL) models gain traction across more industries, there is a growing need for reliable agent-explanation techniques to understand these models. Researchers have developed explainable artificial intelligence (XAI) methods to help understand these 'black boxes'. While these models have been tested on many supervised learning tasks, there is a lack of examination of how these well these methods can explain hard reinforcement learning problems like robotic control. The sequential nature of learning RL policies and testing episodes create fundamentally different policies over time compared to more traditional supervised learning models. In this thesis, two important questions are …