Computer Sciences Commons^™

Sccad: Cluster Decomposition-Based Anomaly Detection For Rare Cell Identification In Single-Cell Expression Data, Yunpei Xu, Shaokai Wang, Qilong Feng, Jiazhi Xia, Yaohang Li, Hong-Dong Li, Jianxin Wang

Computer Science Faculty Publications

Single-cell RNA sequencing (scRNA-seq) technologies have become essential tools for characterizing cellular landscapes within complex tissues. Large-scale single-cell transcriptomics holds great potential for identifying rare cell types critical to the pathogenesis of diseases and biological processes. Existing methods for identifying rare cell types often rely on one-time clustering using partial or global gene expression. However, these rare cell types may be overlooked during the clustering phase, posing challenges for their accurate identification. In this paper, we propose a Cluster decomposition-based Anomaly Detection method (scCAD), which iteratively decomposes clusters based on the most differential signals in each cluster to effectively separate …

Retrogressive Document Manipulation Of Us Federal Environmental Websites, Lesley Frew, Michael L. Nelson, Michele C. Weigle

Computer Science Faculty Publications

Changes made to webpages can affect their retrievability. Often this is done with the intention of increasing the page's search engine ranking to improve overall access to information on the page. The Environmental Data and Governance Initiative (EDGI) created a dataset that describes changes on US federal environmental webpages between 2016 and 2020. EDGI noted that many environmental terms were deleted from the pages, but without user data, claims that page retrievability and public information access were lowered are only anecdotal. The Open Resource for Click Analysis in Search (ORCAS) dataset was created during the same time frame, from 2017 …

Dilf: Differentiable Rendering-Based Multi-View Image-Language Fusion For Zero-Shot 3d Shape Understanding, Xin Ning, Zaiyang Yu, Lusi Li, Weijun Li, Prayag Tiwari

Computer Science Faculty Publications

Zero-shot 3D shape understanding aims to recognize “unseen” 3D categories that are not present in training data. Recently, Contrastive Language–Image Pre-training (CLIP) has shown promising open-world performance in zero-shot 3D shape understanding tasks by information fusion among language and 3D modality. It first renders 3D objects into multiple 2D image views and then learns to understand the semantic relationships between the textual descriptions and images, enabling the model to generalize to new and unseen categories. However, existing studies in zero-shot 3D shape understanding rely on predefined rendering parameters, resulting in repetitive, redundant, and low-quality views. This limitation hinders the model’s …

A Survey On Few-Shot Class-Incremental Learning, Songsong Tian, Lusi Li, Weijun Li, Hang Ran, Xin Ning, Prayag Tiwari

Computer Science Faculty Publications

Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks from just a few labeled samples without forgetting the previously learned ones. This setup can easily leads to catastrophic forgetting and overfitting problems, severely affecting model performance. Studying FSCIL helps overcome deep learning model limitations on data volume and acquisition time, while improving practicality and adaptability of machine learning models. This paper provides a comprehensive survey on FSCIL. Unlike previous surveys, we aim to synthesize few-shot learning and incremental …

A Chinese Power Text Classification Algorithm Based On Deep Active Learning, Song Deng, Qianliang Li, Renjie Dai, Siming Wei, Di Wu, Yi He, Xindong Wu

Computer Science Faculty Publications

The construction of knowledge graph is beneficial for grid production, electrical safety protection, fault diagnosis and traceability in an observable and controllable way. Highly-precision text classification algorithm is crucial to build a professional knowledge graph in power system. Unfortunately, there are a large number of poorly described and specialized texts in the power business system, and the amount of data containing valid labels in these texts is low. This will bring great challenges to improve the precision of text classification models. To offset the gap, we propose a classification algorithm for Chinese text in the power system based on deep …

Building Datasets To Support Information Extraction And Structure Parsing From Electronic Theses And Dissertations, William A. Ingram, Jian Wu, Sampanna Yashwant Kahu, Javaid Akbar Manzoor, Bipasha Banerjee, Aman Ahuja, Muntabir Hasan Choudhury, Lamia Salsabil, Winston Shields, Edward A. Fox

Computer Science Faculty Publications

Despite the millions of electronic theses and dissertations (ETDs) publicly available online, digital library services for ETDs have not evolved past simple search and browse at the metadata level. We need better digital library services that allow users to discover and explore the content buried in these long documents. Recent advances in machine learning have shown promising results for decomposing documents into their constituent parts, but these models and techniques require data for training and evaluation. In this article, we present high-quality datasets to train, evaluate, and compare machine learning methods in tasks that are specifically suited to identify and …

Identifying Patterns For Neurological Disabilities By Integrating Discrete Wavelet Transform And Visualization, Soo Yeon Ji, Sampath Jayarathna, Anne M. Perrotti, Katrina Kardiasmenos, Dong Hyun Jeong

Computer Science Faculty Publications

Neurological disabilities cause diverse health and mental challenges, impacting quality of life and imposing financial burdens on both the individuals diagnosed with these conditions and their caregivers. Abnormal brain activity, stemming from malfunctions in the human nervous system, characterizes neurological disorders. Therefore, the early identification of these abnormalities is crucial for devising suitable treatments and interventions aimed at promoting and sustaining quality of life. Electroencephalogram (EEG), a non-invasive method for monitoring brain activity, is frequently employed to detect abnormal brain activity in neurological and mental disorders. This study introduces an approach that extends the understanding and identification of neurological disabilities …

Triphlapan: Predicting Hla Molecules Binding Peptides Based On Triple Coding Matrix And Transfer Learning, Meng Wang, Chuqi Lei, Jianxin Wang, Yaohang Li, Min Li

Computer Science Faculty Publications

Human leukocyte antigen (HLA) recognizes foreign threats and triggers immune responses by presenting peptides to T cells. Computationally modeling the binding patterns between peptide and HLA is very important for the development of tumor vaccines. However, it is still a big challenge to accurately predict HLA molecules binding peptides. In this paper, we develop a new model TripHLApan for predicting HLA molecules binding peptides by integrating triple coding matrix, BiGRU + Attention models, and transfer learning strategy. We have found the main interaction site regions between HLA molecules and peptides, as well as the correlation between HLA encoding and binding …

Learning Optimal Inter-Class Margin Adaptively For Few-Shot Class-Incremental Learning Via Neural Collapse-Based Meta-Learning, Hang Ran, Weijun Li, Lusi Li, Songsong Tian, Xin Ning, Prayag Tiwari

Computer Science Faculty Publications

Few-Shot Class-Incremental Learning (FSCIL) aims to learn new classes incrementally with a limited number of samples per class. It faces issues of forgetting previously learned classes and overfitting on few-shot classes. An efficient strategy is to learn features that are discriminative in both base and incremental sessions. Current methods improve discriminability by manually designing inter-class margins based on empirical observations, which can be suboptimal. The emerging Neural Collapse (NC) theory provides a theoretically optimal inter-class margin for classification, serving as a basis for adaptively computing the margin. Yet, it is designed for closed, balanced data, not for sequential or few-shot …

Robots Still Outnumber Humans In Web Archives In 2019, But Less Than In 2015 And 2012, Himarsha R. Jayanetti, Kritika Garg, Sawood Alam, Michael L. Nelson, Michele C. Weigle

Computer Science Faculty Publications

The significance of the web and the crucial role of web archives in its preservation highlight the necessity of understanding how users, both human and robot, access web archive content, and how best to satisfy this disparate needs of both types of users. To identify robots and humans in web archives and analyze their respective access patterns, we used the Internet Archive’s (IA) Wayback Machine access logs from 2012, 2015, and 2019, as well as Arquivo.pt’s (Portuguese Web Archive) access logs from 2019. We identified user sessions in the access logs and classified those sessions as human or robot based …

Osfs-Vague: Online Streaming Feature Selection Algorithm Based On A Vague Set, Jie Yang, Zhijun Wang, Guoyin Wang, Yanmin Liu, Yi He, Di Wu

Computer Science Faculty Publications

Online streaming feature selection (OSFS), as an online learning manner to handle streaming features, is critical in addressing high-dimensional data. In real big data-related applications, the patterns and distributions of streaming features constantly change over time due to dynamic data generation environments. However, existing OSFS methods rely on presented and fixed hyperparameters, which undoubtedly lead to poor selection performance when encountering dynamic features. To make up for the existing shortcomings, the authors propose a novel OSFS algorithm based on vague set, named OSFS-Vague. Its main idea is to combine uncertainty and three-way decision theories to improve feature selection from the …

A-Disetrac Advanced Analytic Dashboard For Distributed Eye Tracking, Yasasi Abeysinghe, Bhanuka Mahanama, Gavindya Jayawardena, Yasith Jayawardena, Mohan Sunkara, Andrew T. Duchowski, Vikas Ashok, Sampath Jayarathna

Computer Science Faculty Publications

Understanding how individuals focus and perform visual searches during collaborative tasks can help improve user engagement. Eye tracking measures provide informative cues for such understanding. This article presents A-DisETrac, an advanced analytic dashboard for distributed eye tracking. It uses off-the-shelf eye trackers to monitor multiple users in parallel, compute both traditional and advanced gaze measures in real-time, and display them on an interactive dashboard. Using two pilot studies, the system was evaluated in terms of user experience and utility, and compared with existing work. Moreover, the system was used to study how advanced gaze measures such as ambient-focal coefficient K …

Autonomous Strike Uavs In Support Of Homeland Security Missions: Challenges And Preliminary Solutions, Meshari Aljohani, Ravi Mukkamala, Stephan Olariu

Computer Science Faculty Publications

Unmanned Aerial Vehicles (UAVs) are becoming crucial tools in modern homeland security applications, primarily because of their cost-effectiveness, risk reduction, and ability to perform a wider range of activities. This study focuses on the use of autonomous UAVs to conduct, as part of homeland security applications, strike missions against high-value terrorist targets. Owing to developments in ledger technology, smart contracts, and machine learning, activities formerly carried out by professionals or remotely flown UAVs are now feasible. Our study provides the first in-depth analysis of the challenges and preliminary solutions for the successful implementation of an autonomous UAV mission. Specifically, we …

Mosaic: A Prune-And-Assemble Approach For Efficient Model Pruning In Privacy-Preserving Deep Learning, Yifei Cai, Qiao Zhang, Rui Ning, Chunsheng Xin, Hongyi Wu

Computer Science Faculty Publications

To enable common users to capitalize on the power of deep learning, Machine Learning as a Service (MLaaS) has been proposed in the literature, which opens powerful deep learning models of service providers to the public. To protect the data privacy of end users, as well as the model privacy of the server, several state-of-the-art privacy-preserving MLaaS frameworks have also been proposed. Nevertheless, despite the exquisite design of these frameworks to enhance computation efficiency, the computational cost remains expensive for practical applications. To improve the computation efficiency of deep learning (DL) models, model pruning has been adopted as a strategic …

Speculative Anisotropic Mesh Adaptation On Shared Memory For Cfd Applications, Christos Tsolakis, Nikos Chrisochoides

Computer Science Faculty Publications

Efficient and robust anisotropic mesh adaptation is crucial for Computational Fluid Dynamics (CFD) simulations. The CFD Vision 2030 Study highlights the pressing need for this technology, particularly for simulations targeting supercomputers. This work applies a fine-grained speculative approach to anisotropic mesh operations. Our implementation exhibits more than 90% parallel efficiency on a multi-core node. Additionally, we evaluate our method within an adaptive pipeline for a spectrum of publicly available test-cases that includes both analytically derived and error-based fields. For all test-cases, our results are in accordance with published results in the literature. Support for CAD-based data is introduced, and its …

Charged Track Reconstruction With Artificial Intelligence For Clas12, Gagik Gavalian, Polykarpos Thomadakis, Angelos Angelopoulos, Nikos Chrisochoides

Computer Science Faculty Publications

In this paper, we present the results of charged particle track reconstruction in CLAS12 using artificial intelligence. In our approach, we use neural networks working together to identify tracks based on the raw signals in the Drift Chambers. A Convolutional Auto-Encoder is used to de-noise raw data by removing the hits that do not satisfy the patterns for tracks, and second Multi-Layer Perceptron is used to identify tracks from combinations of clusters in the drift chambers. Our method increases the tracking efficiency by 50% for multi-particle final states already conducted experiments. The de-noising results indicate that future experiments can run …

Simulation-Based Adaptive Interface For Personalized Learning Of Ai Fundamentals In Secondary School, Sara Guerreiro-Santalla, Dalila Duraes, Helen Crompton, Paulo Novais, Francisco Bellas

STEMPS Faculty Publications

This paper presents the first results on the validation of a new Adaptive E-learning System, focused on providing personalized learning to secondary school students in the field of education about AI by means of an adaptive interface based on a 3D robotic simulator. The prototype tool presented here has been tested at schools in USA, Spain, and Portugal, obtaining very valuable insights regarding the high engagement level of students in programming tasks when dealing with the simulated interface. In addition, it has been shown the system reliability in terms of adjusting the students’ learning paths according to their skills and …

The Transformative Integration Of Artificial Intelligence With Cmmc And Nist 800-171 For Advanced Risk Management And Compliance, Mia Lunati

Cybersecurity Undergraduate Research Showcase

This paper explores the transformative potential of integrating Artificial Intelligence (AI) with established cybersecurity frameworks such as the Cybersecurity Maturity Model Certification (CMMC) and the National Institute of Standards and Technology (NIST) Special Publication 800-171. The thesis argues that the relationship between AI and these frameworks has the capacity to transform risk management in cybersecurity, where it could serve as a critical element in threat mitigation. In addition to addressing AI’s capabilities, this paper acknowledges the risks and limitations of these systems, highlighting the need for extensive research and monitoring when relying on AI. One must understand boundaries when integrating …

The Vulnerabilities To The Rsa Algorithm And Future Alternative Algorithms To Improve Security, James Johnson

Cybersecurity Undergraduate Research Showcase

The RSA encryption algorithm has secured many large systems, including bank systems, data encryption in emails, several online transactions, etc. Benefiting from the use of asymmetric cryptography and properties of number theory, RSA was widely regarded as one of most difficult algorithms to decrypt without a key, especially since by brute force, breaking the algorithm would take thousands of years. However, in recent times, research has shown that RSA is getting closer to being efficiently decrypted classically, using algebraic methods, (fully cracked through limited bits) in which elliptic-curve cryptography has been thought of as the alternative that is stronger than …

The Underrepresentation Of Black Females In Cybersecurity, Makendra Latrice Crosby

Cybersecurity Undergraduate Research Showcase

The significance of cybersecurity methods, strategies, and programs in protecting computers and electronic devices is crucial throughout the technological infrastructure. Despite the considerable growth in the cybersecurity field and its expansive workforce, there exists a notable underrepresentation, specifically among Black/African American females. This study examines the barriers hindering the inclusion of Black women in the cybersecurity workforce such as socioeconomic factors, limited educational access, biases, and workplace culture. The urgency of addressing these challenges calls for solutions such as education programs, mentorship initiatives, creating inclusive workplace environments, and promoting advocacy and increased awareness within the cybersecurity field. Additionally, this paper …

Rising Threat - Deepfakes And National Security In The Age Of Digital Deception, Dougo Kone-Sow

Cybersecurity Undergraduate Research Showcase

This paper delves into the intricate landscape of deepfakes, exploring their genesis, capabilities, and far-reaching implications. The rise of deepfake technology presents an unprecedented threat to American national security, propagating disinformation and manipulation across various media formats. Notably, deepfakes have evolved from a historical backdrop of disinformation campaigns, merging with the advancements of artificial intelligence (AI) and machine learning to craft convincing but false multimedia content.

Examining the capabilities of deepfakes reveals their potential for misuse, evidenced by instances targeting individuals, companies, and even influencing political events like the 2020 U.S. elections. The paper highlights the direct threats posed by …

New Paths Of Attacks: Revealing The Adaptive Integration Of Artificial Intelligence In Evolving Cyber Threats Targeting Social Media Users And Their Data, Larry Teasley

Cybersecurity Undergraduate Research Showcase

The intersection between artificial intelligence tools and social media has opened doors to numerous opportunities and risks. This research delves into the escalating threat landscape in a society heavily dependent on social media. Despite the efforts by social media companies and cybersecurity professionals to mitigate cyber-attacks, the constant advancements of new technologies render social media platforms increasingly vulnerable. Malicious actors exploit generative AI to collect user data, enhancing cyber threats on social media. Notably, generative AI amplifies phishing attacks, disseminates false information, and propagates propaganda, posing substantial challenges to platform security. Ease access to large language models (LLMs) further complicates …

Lip(S) Service: A Socioethical Overview Of Social Media Platforms’ Censorship Policies Regarding Consensual Sexual Content, Sage Futrell

Cybersecurity Undergraduate Research Showcase

The regulation of sexual exploitation on social media is a pressing issue that has been addressed by government legislation. However, laws such as FOSTA-SESTA has inadvertently restricted consensual expressions of sexuality as well. In four social media case studies, this paper investigates the ways in which marginalized groups have been impacted by changing censorship guidelines on social media, and how content moderation methods can be inclusive of these groups. I emphasize the qualitative perspectives of sex workers and queer creators in these case studies, in addition to my own experiences as a content moderation and social media management intern for …

Privacy Concerns And Proposed Solutions With Iot In Wearable Technology, Hyacinth Abad

Cybersecurity Undergraduate Research Showcase

This paper examines the dynamic relationship between IoT cybersecurity and privacy concerns associated with wearable devices. IoT, with its exponential growth, presents both opportunities and challenges in terms of accessibility, integrity, availability, scalability, confidentiality, and interoperability. Cybersecurity concerns arise as diverse attack surfaces exploit vulnerabilities in IoT systems, necessitating robust defenses. In the field of wearable technology, these devices offer benefits like health data tracking and real-time communication. However, the adoption of these devices raises privacy concerns. The paper explores proposed solutions, including mechanisms for user-controlled data collection, the implementation of Virtual Trip Line (VTL) and virtual wall approaches, and …

A Review Of Threat Vectors To Dna Sequencing Pipelines, Tyler Rector

Cybersecurity Undergraduate Research Showcase

Bioinformatics is a steadily growing field that focuses on the intersection of biology with computer science. Tools and techniques developed within this field are quickly becoming fixtures in genomics, forensics, epidemiology, and bioengineering. The development and analysis of DNA sequencing and synthesis have enabled this significant rise in demand for bioinformatic tools. Notwithstanding, these bioinformatic tools have developed in a research context free of significant cybersecurity threats. With the significant growth of the field and the commercialization of genetic information, this is no longer the case. This paper examines the bioinformatic landscape through reviewing the biological and cybersecurity threats within …

Integrating Ai Into Uavs, Huong Quach

Cybersecurity Undergraduate Research Showcase

This research project explores the application of Deep Learning (DL) techniques, specifically Convolutional Neural Networks (CNNs), to develop a smoke detection algorithm for deployment on mobile platforms, such as drones and self-driving vehicles. The project focuses on enhancing the decision-making capabilities of these platforms in emergency response situations. The methodology involves three phases: algorithm development, algorithm implementation, and testing and optimization. The developed CNN model, based on ResNet50 architecture, is trained on a dataset of fire, smoke, and neutral images obtained from the web. The algorithm is implemented on the Jetson Nano platform to provide responsive support for first responders. …

Potential Security Vulnerabilities In Raspberry Pi Devices With Mitigation Strategies, Briana Tolleson

Cybersecurity Undergraduate Research Showcase

For this research project I used a Raspberry Pi device and conducted online research to investigate potential security vulnerabilities along with mitigation strategies. I configured the Raspberry Pi by using the proper peripherals such as an HDMI cord, a microUSB adapter that provided 5V and at least 700mA of current, a TV monitor, PiSwitch, SD Card, keyboard, and mouse. I installed the Rasbian operating system (OS). The process to install the Rasbian took about 10 minutes to boot starting at 21:08 on 10/27/2023 and ending at 21:18. 1,513 megabytes (MB) was written to the SD card running at (2.5 MB/sec). …

How Chatgpt Can Be Used As A Defense Mechanism For Cyber Attacks, Michelle Ayaim

Cybersecurity Undergraduate Research Showcase

The powers of OpenAI's groundbreaking AI language model, ChatGPT, startled millions of users when it was released in November. But for many, the tool's ability to further accomplish the goals of evil actors swiftly replaced their initial excitement with significant concerns. ChatGPT gives malicious actors additional ways to possibly compromise sophisticated cybersecurity software. Leaders in a sector that is currently suffering from a 38% global spike in data breaches in 2022 must acknowledge the rising influence of AI and take appropriate action. Cybercriminals are writing more complex and focused business email compromise (BEC) and other phishing emails with the assistance …

The Analysis And Impact Of Artificial Intelligence On Job Loss, Ava Baratz

Cybersecurity Undergraduate Research Showcase

This paper illustrates the analysis and impact of Artificial Intelligence (AI) on job loss across various industries. This paper will discuss an overview of AI technology, a brief history of AI in industry, the positive impacts of AI, the negative impacts of AI on employment, AI considerations that contribute to job loss, the future outlook of AI, and employment loss mitigation strategies Various professional source articles and reputable blog posts will be used to finalize research on this topic.

The Propagation And Execution Of Malware In Images, Piper Hall

Cybersecurity Undergraduate Research Showcase

Malware has become increasingly prolific and severe in its consequences as information systems mature and users become more reliant on computing in their daily lives. As cybercrime becomes more complex in its strategies, an often-overlooked manner of propagation is through images. In recent years, several high-profile vulnerabilities in image libraries have opened the door for threat actors to steal money and information from unsuspecting users. This paper will explore the mechanisms by which these exploits function and how they can be avoided.