Digital Commons Network^™

Stylespade: Realistic Image Augmentation For Robust Infrastructure Crack Segmentation Via Ensemble Learning, Jaeung Sim, Menas Kafatos, Seung Hee Kim, Yangwon Lee

Institute for ECHO Articles and Research

The rapid deterioration of global infrastructure necessitates precise and automated crack detection technologies for proactive maintenance. However, deep learning-based segmentation models often suffer from a scarcity of diverse, high-quality labeled datasets. This study proposes StyleSPADE, a novel conditional image generation model that integrates semantic masks and style images to synthesize realistic crack data with diverse background textures while preserving precise geometric morphology. To validate the effectiveness of the generated data, we conducted extensive semantic segmentation tasks using Transformer-based (Mask2Former, Swin-UPerNet) and CNN-based (K-Net) models. Experimental results demonstrate that StyleSPADE-based augmentation significantly outperforms baseline models, achieving a Crack IoU of 0.6376 …

Developing Pattern Recognition And Interpretable Convolutional Neural Network Based Frameworks For Identifying Drug Resistant And Pan Cancer Mirnas From Expression Data, Joginder Jsingh

Doctoral Theses

Micro Ribonucleic Acids (miRNAs) are short length (∼24) non-coding RNAs and are considered as key biomarkers in cancer diagnosis and treatment. They play a vital role in classifying cancer patients from normal ones and drug resistant patients from control ones. The control patients are those who have not received any drug for cancer treatment. The objective is to identify a subset of miRNAs those help in the classification of the patients using expression data. The thesis is comprised of four contributory chapters in addition to an introduction and conclusion. In the first two contributory chapters, computational methods for ranking and …

Environmental Degradations In Images: Analysis, Restoration, And Applications, Harsh Bhandari

Doctoral Theses

This thesis investigates computational models and methodologies for restoring images degraded by challenging environmental conditions such as haze and underwater environments. It further explores the analysis and estimation of particulate matter (PM) concentration from both day and night scenes under varying weather conditions, using degraded visual data as a primary input. Each environment introduces distinct forms of visual degradation, making image restoration a critical challenge that directly impacts applications including visibility enhancement, weather analysis, particulate concentration estimation, and object detection. By addressing these challenges, this thesis aims to develop adaptable, data-driven solutions that enhance image clarity and improve information extraction …

Are You An Ai Convert Yet?, Essraa Nawar

Library Articles and Research

"At one point that evening, after the conversation had moved from travel to work and then to responsibility, Marium paused and asked me what I did. It was not the transactional question that so often fills conference hallways, asked politely and quickly abandoned, but a genuine inquiry. When I told her that I chair the Artificial Intelligence Committee at Leatherby Libraries at Chapman University, and that my work centers on AI literacy, governance, and institutional decision-making rather than promotion or blind adoption, something subtle changed."

Confluence, Vol. 4, Iss. 2, Full Issue

The Confluence

No abstract provided.

A Review Of Routing Attacks In Routing Protocol Over Low-Power And Lossy-Based Iot Networks, Lanka Chris Sejaphala Mr., Vusimuzi Malele Prof, Francis Lugayizi Prof.

Journal of Cybersecurity Education, Research and Practice

Low-power and Lossy IoT Networks (LLNs) comprise physical sensors, processing capability, power, and other technologies to exchange information between systems and devices over the internet. However, these networks are susceptible to routing attacks affecting resources, traffic flow, and topology formation. In the related work, it has been discovered that many previous studies do not consider algorithms and implementation approaches for routing attacks. This research study provides a comprehensive in-depth synthesis insight into the description, effects, and algorithms & implementation of four routing attacks in LLNs i.e., rank, sinkhole, DIS-flooding, and worst parent attacks. The findings of this research study highlight …

Wild@Fire2025: Overview Of Word-Level Code-Mixed Language Identification In Dravidian Languages, Ameeta Agrawal, Asha Hegde, Sharal Coelho, Sabur Butt, Fazlourrahman Balouchzahi, Sudha V, Shashirekha Hosahalli Lakshmaiah

Computer Science Faculty Publications and Presentations

Code-mixing is considered as a linguistic phenomenon that combines several languages into one text. It has now become very common in multilingual societies, especially in digital communication. Word-Level Identification of Languages in Dravidian Languages (WILD) - a Code-mixed Language Identification (CoLI) in Dravidian languages shared task, organized as a part of Forum for Information Retrieval and Evaluation (FIRE) 2025, put forward these challenges to the researchers by asking them to develop models capable of classifying words in code-mixed texts involving Dravidian languages - Tamil, Telugu, Malayalam, Kannada, and Tulu, which are interwoven with English. It poses significant challenges due to …

Reformulation Of The Protein Databank For Real-Time Search Of Geometrical Attributes Of Protein Structures, Musa Azeem, Christopher Lee, Aaron Hein, Christopher Ott, Homayoun Valafar

Faculty Publications

Introduction:

In this study, we introduce the design and implementation of PDBMine, a large-scale, queryable platform for mining sequence-structure statistics from the Protein Data Bank (PDB). PDBMine enables rapid analysis of local conformational trends across proteins by extracting dihedral angles and sequence patterns at scale. In addition to the design and implementation of PDBMine, we also present results validating its ability to return structurally meaningful information.

Methods:

We first assess the accuracy of its dihedral angle distributions by comparing them to established Ramachandran space and verifying expected behaviors of residues such as glycine and proline. We then use PDBMine to …

Densest Subgraph Discovery On The Cpu, Hunter Gerard Gareau

Theses and Dissertations

The Densest Subgraph Discovery (DSD) problem is a prevalent problem in the field of graph mining, aiming to find the cohesive subgraph. Given a graph �� = (��,��) and an integer �� ≥ 2, the goal is to find a vertex sub- set �� ⊆ �� whose induced subgraph �� (��) maximizes the ��-clique density, defined as the number of ��-cliques per vertex. Larger val- ues of �� capture higher-order connectivity patterns beyond edges, enabling the discovery of more cohesive structures. There have been many solutions to this problem. However, one avenue that other graph mining problems have gone down …

Antibacterial Peptides From Soybean (Glycine Max (L.) Merr.) With In Silico Study Against Escherichia Coli Bacteria, Dian Riana Ningsih, Ely Setiawan, Purwati Purwati, Zusfahair Zusfahair, Anita Hindayanti Rukmana

Karbala International Journal of Modern Science

Bioactive peptides are produced from soy milk protein hydrolysis using trypsin. The research began with the preparation and separation of soy milk protein, followed by fractionation using ammonium sulphate, protein hydrolysis, and SDS-PAGE analysis of protein hydrolysates. Fractions exhibiting the highest degree of hydrolysis were further fractionated by SPE and tested to determine the antibacterial activity Staphylococcus aureus and Escherichia coli. The peptide sequence of the active peptide as an antibacterial was identified, employing LC-HRMS. The mode of action between active peptides and bacterial membran was analysed using molecular dynamics (MD) simulation. The findings displayed that F15 contained the highest …

Jiving With Llms: Assessing First Year Students’ Computer Programming Self Efficacy After Reading Code With Llms, Michelle Jarvie-Eggart, Joseph Roy Teahen, Daniel T. Masker, Jose Padilla, Leo C. Ureel Ii, Laura E. Brown, Scott Pomerville, Jon Sticken

Michigan Tech Publications

This study investigated the impact of leveraging generative artificial intelligence (GenAI) to assist 1st-year engineering and computer science (CS) students in reading code in a new (to them) language. Students were asked to comment code in FORTRAN. They were then asked to run the code through ChatGPT-4.0 for its comments and reflect on what they learned from the experience. Participants completed survey items from Ramalingam and Wiedenbeck’s Computer Programming Self-Efficacy Scale (CPSES) prior to and after the intervention. Additional open-ended reflective (qualitative) questions were added to the quantitative questions in the postintervention questionnaire. This study documents increases in self-efficacy for …

Utilizing Machine Learning Techniques For Computer-Aided Covid-19 Screening Based On Clinical Data, Honglun Xu, Andrews T. Anum, Michael Pokojovy, Sreenath Chalil Madathil, Yuxin Wen, Md. Fashiar Rahman, Tzu-Liang Bill Tseng, Scott Moen, Eric Walser

Engineering Faculty Articles and Research

The COVID-19 pandemic has highlighted the importance of rapid clinical decision-making to facilitate the efficient usage of healthcare resources. Over the past decade, machine learning (ML) has caused a tectonic shift in healthcare, empowering data-driven prediction and decision-making. Recent research demonstrates how ML was used to respond to the COVID-19 pandemic. This paper puts forth new computer-aided COVID-19 disease screening techniques using six classes of ML algorithms (including penalized logistic regression, random forest, artificial neural networks, and support vector machines) and evaluates their performance when applied to a real-world clinical dataset containing patients’ demographic information and vital indices (such as …

Optimized Resnet-18 Architecture For Multi-Class Oral Diseases Classification, Ahmed Ahmed

Karbala International Journal of Modern Science

In recent years, the classification of oral diseases has gained significant attention due to its influence on public health and the necessity for early and accurate diagnosis. Traditional diagnosis depends on manual clinical assessment, which can be slow and subjective. An optimized and subsequently quantized model is required to provide a faster and more consistent diagnostic support tool. This paper proposes an optimized ResNet-18 architecture for the classification of six oral diseases. The optimization process is based on removing the Rectified Linear Unit (ReLU), Batch Normalization (BN), and convolutional layers from the base ResNet-18 blocks that contain 128 filters. This …

Sperm-Associated Antigen 6 (Spag6) As A Potential Marker Of Sperm Function In Diagnosing Male Infertility, Ibtisam A. Al-Ali,, Kawkab A. Alsaadi

Karbala International Journal of Modern Science

Background: While male infertility has become a significant global health concern, conventional analysis of semen has not made progress in the detection of contraindicated molecular biomarkers, such as sperm-associated antigen 6 (SPAG6), which is a protein involved in axonemal structure and flagellar motility.

Hypothesis: Expression of SPAG6 correlates with sperm motility and structural integrity. This means that its dysregulation may serve as a molecular indicator of impaired sperm performance.

Methods: A comprehensive review of recent studies was conducted with a focus on SPAG6’s molecular characteristics, expression patterns in normal versus abnormal spermatozoa, and the role it plays in motility-related …

Optimized Co2 Gas Sensing With Sns:Sm2o3/N-Si Nanocomposites Fabricated Via Spray Pyrolysis, Wasan A. Khalaf, Mays A. Hammadi, Mohammed J. Alsultani, Yahya R. Hathal, Mohammed O. Salman

Karbala International Journal of Modern Science

In this work, tin sulfide:samarium oxide (SnS:Sm₂O₃) composite films were deposited using a spray pyrolysis technique for room-temperature CO₂ gas sensing. X-ray diffraction (XRD) confirmed a polycrystalline SnS nature of orthorhombic-phase crystallinity at 10 at.% Sm ions, while 20 at.% Sm induced Sm₂O₃ as a separate phase. Field emission-scanning electron microscopy (FE-SEM) induced uniform grains and increased the surface roughness, enhancing gas adsorption. UV-visible absorbance revealed band-gap narrowing. Fourier transform infrared spectroscopy (FTIR) analysis revealed vibrational band shifts, confirming the structural modifications. Gas-sensing measurements demonstrated 5.72%, 19.65%, and 9.65% for pure SnS, …

Appropriate Wireless Technology For Blue Data Communication To Enhance Artisanal Fishery, Abdi T. Abdalla, Eva Shayo, Angelina Misso, Baraka Maiseli, Kwame S. Ibwe, Narriman Jiddawi, Moses Ismail

Tanzania Journal of Science

The paper examines the development of a system architecture to support smart fishing. This includes the establishment of a blue data center, which would allow government agencies and research institutions to access fisheries data. The goal is to provide policymakers with the tools they need to efficiently manage artisanal fisheries resources. The architecture also incorporates wireless communication components that are suitable for small-scale fishers in remote areas. The study delves into the selection of appropriate wireless communication technology for transmitting fishing data to the communication center. Factors such as coverage range, data rates, and cost implications are taken into consideration. …

Bridging The Gap: A Systematic Review Of Cyber Conflict Forecasting Models And The Case For Ai-Driven Dynamic Frameworks, Salim Arfaoui, Youssef Harrath, Omar El-Gayar

Research & Publications

Cyber conflict forecasting remains constrained by static models that overlook the integration of geopolitical context with technical indicators. This systematic literature review examines 58 studies (2010–2025) using PRISMA guidelines and an InputProcess-Output framework to classify approaches and identify key gaps. Quantitative methods dominate (67%), yet only 14% incorporate geopolitical variables, despite the political nature of cyber conflict. Major limitations include adversarial adaptation blindness (85% assume static behavior), coarse temporal granularity (72% use daily+ intervals), lack of uncertainty quantification (75%), and minimal modeling of cross-domain escalation (92% cyber-only focus). Strategic forecasting is rare, with just 14% providing long-term insights and 16% …

Pciafl: Personalized And Class Imbalance-Aware Federated Learning For Driver Behavior Classification, Osho Osho, Shubh Garg, Suchetana Chakraborty, Sajal K. Das

Computer Science Faculty Research & Creative Works

Automated understanding of driver behavior from vehicular kinematics is vital for safety-aware intelligent transportation systems. However, centralized cloud processing suffers from latency, scalability, and privacy issues. Federated Learning (FL) provides a decentralized alternative but faces two major challenges: (i) non-IID client data due to heterogeneous driving styles and sensors, and (ii) severe class imbalance, as risky behaviors are inherently rare. In this work, we propose a personalized FL framework that uses a shared CNN-LSTM backbone with client-adaptive classifiers and incorporates a cost-sensitive loss to address behavior skew. Evaluated on the UAH-DriveSet dataset, our method achieves 92.60% accuracy and 91.68% macro-F1, …

Datamut: Deterministic Algorithms For Time-Delay Attack Detection In Multi-Hop Uav Networks, Keiwan Soltani, Federico Corò, Punyasha Chatterjee, Sajal K. Das

Computer Science Faculty Research & Creative Works

Unmanned Aerial Vehicles (UAVs), also known as drones, have gained popularity in various fields such as agriculture, emergency response, and search and rescue operations. UAV networks are susceptible to potential security threats, such as wormhole attacks, jamming, spoofing, and false data injection. Time-Delay Attack (TDA) is a unique attack in which malicious UAVs intentionally delay packet forwarding, posing significant threats, especially in time-sensitive applications. It is challenging to distinguish malicious delay from benign network delay due to the dynamic nature of UAV networks, intermittent wireless connectivity, or the Store-Carry-Forward (SCF) mechanism during multi-hop communication. Some existing works propose machine learning-based …

Rescue: Routing Under Evolving Stochastic Congestion And Uncertain Spread In Wildfire Emergencies, Sowjanya Tammali, Arindam Khanda, Anurag Satpathy, S. M. Shovan, Sajal K. Das

Computer Science Faculty Research & Creative Works

Wildfires cause unpredictable spread and panic-driven congestion, posing severe challenges to evacuation planning. We present RESCUE (Routing under Evolving Stochastic Congestion and Uncertain Spread in Wildfire Emergencies), a dynamic, risk-aware framework that models the road network as a time-varying weighted graph. RESCUE operates in two stages: (i) a preprocessing phase integrating fire forecasts, traffic density, and distance to assign edge weights, and (ii) a real-time routing phase that adaptively updates paths using a multi-granular strategy distinguishing macro-level disruptions (e.g., rapid spread) from micro-level changes (e.g., local congestion). Two stochastic edge-cost functions are introduced: the Edge-Fire Risk Function (EFRF), estimating road …

Optimizing Proaftn Classifier With Ant Colony Algorithm: Enhanced Diabetes Detection Benchmarking, Feras Al-Obeidat

All Works

The increasing global prevalence of diabetes highlights the need for accurate diagnostic tools to improve early detection and effective treatment planning. Traditional classification models often struggle to achieve optimal performance due to limitations in parameter tuning and adaptability to complex datasets. To address these limitations, this article introduces PROAnt, an innovative learning approach designed to enhance the robustness and efficiency of the PROAFTN multicriteria classification method. PROAnt leverages the computational power of ant colony optimization (ACO) to dynamically fine-tune and optimize the key parameters, such as intervals and weights, at the core of the PROAFTN classification process. This learning methodology …

Task-Optimized Brain Parcellations Reveal Latent Functional Organization For Enhanced Connectivity-Based Neuroimaging Classification, Andrew Hannum, Mario A. Lopez

Computer Science: Faculty Scholarship

Brain parcellation schemes are fundamental to neuroimaging, yet general-purpose atlases may obscure the specific functional architecture relevant to a given cognitive task or clinical condition. This reflects a growing consensus that the “optimal” brain map is context-dependent. Here, we introduce a novel framework that validates this principle by generating task-optimized human brain parcellation maps directly from supervised learning objectives. Our method defines functional parcels by grouping brain regions based on the similarity of their contributions to a classifier's decision boundary for a specific goal (e.g., cognitive state decoding or clinical group separation). This approach prioritizes a region's discriminative role over …

A Visualization-Supported, Hierarchical, Action-Learning Model For Driving Behavior In A V2x Environment, Xuantong Wang, Jing Li, Jecca Bowen

Geography and the Environment: Faculty Scholarship

Understanding human driving decisions is crucial for intelligent transportation research. Most existing studies focus on individual vehicles in limited contexts, which restricts broader applicability of results. Leveraging Vehicle-to-Everything (V2X) infrastructure, this study introduces a machine learning framework to model driving actions and detect outliers across diverse environments. This approach features a semantically enabled clustering method that groups similar driving behaviors based on speed and actions. It also adds a time-series learning model to identify typical driving behaviors across various contexts, thereby enabling detection of abnormal driving actions. A suite of visual tools has been developed to help interpret driving patterns, …

Ai In Society: A Regulatory Framework For Responsible Integration, Ziad Doughan, Sari Itani, Hadi Al Mubasher

BAU Journal - Science and Technology

This review paper studies the influence of Artificial Intelligence (AI) and Machine Learning (ML) on society in various categories in detail. AI and ML have developed rapidly in the past two decades, thus changing our lifestyles. These developments have various positive and negative impacts on society. This paper explores the many societal impacts of AI and ML, in economics, social aspects, ethics, and policy, shedding light on the opportunities and challenges that arise. An interdisciplinary insight is capable of understanding the challenges society faces when it uses AI and ML, locking opportunities that lie ahead and identifying promising paths towards …

Universal Sound Separation: Distance-Aware Mixture Simulation, Co-Occurrence Conditioning, And Chain-Of-Inference, Wonjun Park

Computer Science and Engineering Theses - Archive

Universal Sound Separation (USS) -- the task of disentangling arbitrary sound sources from a single-channel acoustic mixture -- remains an open challenge due to the ill-posed nature of the problem and the distributional gap between synthetic training data and real-world recordings. This thesis addresses three distinct bottlenecks in the USS pipeline: training data realism, inference strategy, and conditioning richness. We first present two knowledge-guided approaches to sound source separation. The first is a distance-aware mixing strategy that leverages Large Language Models (LLMs) to assign plausible loudness relationships between audio sources during training data synthesis. By querying an LLM about the …

A. Vs. I In Ai: Is There A Threshold To "Engineered" Intelligence?, Joshit Mohanty

Engineering Management & Systems Engineering Faculty Publications

Despite artificial intelligence reshaping the world, its development generates uncertainties regarding future capabilities. AI simultaneously exists as an artifact of engineering design and as autonomous intelligence, creating an observer-participant feedback loop. This paper proposes that embodied AI faces a bandwidth-limited intelligence threshold T_h that it arises from B = min(C_sens,C_Act). However, Shannon capacity measures bits while intelligence operates on concepts, necessitating a dual-channel model separating physical bandwidth B_io from representational capacity B_rep. Intelligence emerges as multi-dimensional rather than scalar, with components exhibiting different bandwidth dependencies. Surpassing T_h requires either new sensing methods expanding B, enhanced representational frameworks, or reconceptualization within …

Zero-Shot Segmentation Of Estuary Mudflats Using The Segment Anything Model, Jaren Unzen

Honors Theses and Capstones

Estuary mudflats are ecologically sensitive environments that require consistent monitoring. Traditional satellite-based classification workflows are often constrained by the high cost and labor-intensive nature of manual data annotation. This study evaluates the utility of Segment Anything Model 3 (SAM 3), a foundational computer vision model, to automate mudflat segmentation without domain-specific fine-tuning. By leveraging the model’s text-prompting capabilities alongside specialized pre- and post-processing techniques, we generated segmentation masks in a zero-shot framework. Our approach achieved an F1- score of 0.51, demonstrating the inherent challenges of spectrally complex coastal features. Despite this, the results highlight a promising pathway for adapting large-scale …

Aura: An Ai-Powered Multimodal Prototype For Adaptive Apraxia Of Speech Therapy And Communication Support, Omotayo Omoyemi, Rachel K. Johnson

Speech-Language Pathology Faculty Publications

Apraxia of Speech (AOS) is a motor speech disorder that significantly limits communication and requires intensive, long-term therapy. Access to consistent treatment is often constrained by shortages of speech-language pathologists, high costs, and limited opportunities for continuous monitoring outside clinical settings. Recent advances in Artificial Intelligence (AI) provide new opportunities to support scalable and personalized speech therapy.

This paper presents AURA (Adaptive Understanding and Relearning Assistant for Apraxia), a multimodal AI framework designed to support speech therapy, progress monitoring, and communication for individuals with AOS. The system integrates speech analysis, machine learning–based error detection, reinforcement learning for adaptive therapy, and …

Explaining The Unseen: Multimodal Vision-Language Reasoning For Situational Awareness In Underground Mining Disasters, Mizanur Rahman Jewel, Mohamed Elmahallawy, Sanjay Kumar Madria, Samuel Frimpong

Computer Science Faculty Research & Creative Works

Underground mining disasters produce pervasive darkness, dust, and collapses that obscure vision and make situational awareness difficult for humans and conventional systems. To address this, we propose MDSE, Multimodal Disaster Situation Explainer, a novel vision-language framework that automatically generates detailed textual explanations of post-disaster underground scenes. MDSE has three-fold innovations: (i) Context-Aware Cross-Attention for robust alignment of visual and textual features even under severe degradation; (ii) Segmentation-aware dual pathway visual encoding that fuses global and region-specific embeddings; and (iii) Resource-Efficient Transformer-Based Language Model for expressive caption generation with minimal compute cost. To support this task, we present the Underground Mine …

An Examination Of Ethics When Using Chatgpt, Blake V. Ailes

CCAC Theses and Dissertations

With the general population’s recent and dramatic increase in the frequency of ChatGPT and other similar Artificial Intelligence Generated Content (AIGC) usage throughout various industries, gray areas are becoming more prominent regarding whether ChatGPT is considered to be ethical or unethical in certain situations. Examples of unethical use of ChatGPT include plagiarism, the use of inaccurate information in drawing conclusions, and the creation of malicious code that negatively impacts various companies. Not all of these ethical concerns are necessarily the fault of the user or the AIGC. To date, peer-reviewed research on the ethical usage of ChatGPT is limited, primarily …