Digital Commons Network^™

Roadmap On Artificial Intelligence-Augmented Additive Manufacturing, Ali Zolfagharian, Liuchao Jin, Qi Ge, Wei-Hsin Liao, Andrés Díaz Lantada, Francisco Franco Martínez, Tianyu Zhang, Tao Liu, Charlie C.L. Wang, Mohammad Hossein Mosallanejad, Reza Ghanavati, Abdollah Saboori, Alejandro De Blas De Miguel, William Solórzano-Requejo, Yi Cai, Xiangyang Dong, Huangyi Qu, Najmeh Samadiani, Guangyan Huang, Austin Downey, Yanzhou Fu, Lang Yuan

Faculty Publications

Artificial intelligence-augmented additive manufacturing (AI2AM) represents a transformative frontier in digital fabrication, where artificial intelligence (AI) is embedded not as a peripheral tool, but as a central framework driving intelligent, adaptive, and autonomous additive manufacturing (AM) systems. The objective of this Roadmap is to present a comprehensive vision of the state-of-the-art developments in AI2AM while charting the future trajectory of this rapidly emerging field. As AM applications continue to expand across diverse sectors, conventional design and control strategies face growing limitations in scalability, quality assurance, and material complexity. AI uses tools like computer vision, generative design, and large language models …

Machine Learning For Real-Time Body Movement Classification Using Eeg And Vr Technologies, Aiden H. Behler, Robin Ghosh

Undergraduate Research

This project investigates the feasibility of real-time full-body movement classification using electroencephalography (EEG) integrated with virtual reality (VR) technologies. The primary objective is to develop and evaluate machine learning models for predicting human body movements using EEG data alone, with the long-term goal of reducing or eliminating reliance on wearable motion trackers. Currently, several machine learning algorithms have been tested, but classification accuracy remains modest, indicating the complexity of the task. Ongoing work focuses on optimizing preprocessing, feature selection, and model architectures to improve performance. The system architecture combines synchronized neural and motion data collected within a VR environment. EEG …

Beyond Anomaly Detection: Classifying Attacker Automation Level From Ssh Honeypot Behavioral Signatures, Ashley Alt

Theses

The proliferation of AI-assisted offensive tools has introduced a new category of cyber attacker that combines the speed of automation with the adaptive reasoning previously associated only with skilled human operators. Despite the richness of behavioral data captured by SSH honeypots, existing analyses treat interaction logs primarily as evidence of malicious activity rather than as a dataset capable of distinguishing between attacker types. This thesis investigates whether human-driven, traditionally automated, and AI-assisted attackers produce distinguishable behavioral signatures within SSH honeypot interactions, and whether machine learning techniques can reliably classify attacker behavior from session-level features. A controlled experimental architecture was developed …

Development Of A Novel Cfd Approach For Predicting Multiphase Flow Enhanced By Machine Learning, Abdulrahman Elazazi Salem

Theses

Accurate estimation of interface orientation is crucial for ensuring both the accuracy and robustness of Volume of Fluid (VOF) schemes in multiphase flow simulations, especially when using non-uniform Cartesian meshes. Conventional gradient reconstruction approaches, such as least-squares (LSQ) methods, often suffer from significant errors and strong oscillations on highly stretched grids. This work proposes a grid-transferable, learning-based methodology that predicts interface unit normal vectors directly from the local volume-fraction field on nonuniform structured Cartesian grids using a feedforward neural network. The methodology extends earlier work originally developed for uniform grids, which is first reproduced to assess how performance deteriorates in …

Machine Learning And Multisensor Data Fusion For Forest Above Ground Biomass Estimation In Arkansas, Abdullah Al Saim, Mohamed Aly

Geosciences Faculty Publications and Presentations

Forests are essential for biodiversity conservation, climate change, natural education, scientific research, and carbon sequestration. This study uses machine learning-based Random Forest (RF) regression to estimate the Above Ground Biomass (AGB) of the Ozark and Ouachita forests at a 10-meter resolution by combining data from Sentinel-2, Sentinel-1, and GEDI (Global Ecosystem Dynamics Investigation) on Google Earth Engine. The RF model included 34 out of 154 variables representing topographical, spectral, and textural factors demonstrating strong correlations with measured biomass. The RF model showed strong performance with R-squared and RMSE values of 0.95 and 18.46 for the training dataset and 0.75 and …

Rethinking News Classification Through A Multi-Dimensional Framework, Luana De Jesus Ferreira

Honors Theses

This thesis proposes a multi-dimensional framework for news classification that evaluates articles across three independent dimensions: headline accuracy, language neutrality, and content reliability. These dimensions produce both a continuous reliability score and a five-tier interpretive scale, while additionally classifying articles by genre and topic. To operationalize this framework, a structured annotation protocol was developed and applied to a dataset of 373 news articles drawn from 79 outlets spanning a wide range of contemporary media ecosystem. A binary Logistic Regression classifier trained on the ISOT Fake News Dataset was then evaluated against this dataset to examine how a model trained on …

Advancing Edge Ai Through Integrated Neuromorphic Algorithms And Hardware, Peyton Chandarana

Theses and Dissertations

As machine learning continues to expand across diverse sectors, including healthcare, transportation, environmental monitoring, and consumer electronics, many applications operate under strict constraints on latency, bandwidth, privacy, and power availability. Meeting these demands increasingly requires deploying machine learning at the edge to process data locally rather than relying on remote cloud infrastructure. These limitations highlight the importance of computational efficiency and motivate the exploration of alternative hardware and algorithmic paradigms capable of delivering real-time, accurate inference under tight resource constraints.

Two major paradigms have emerged for edge intelligence: conventional artificial neural networks (ANNs) deployed on highly parallel edge accelerators such …

Advanced Artificial Intelligence Vs Simpler Models For 1-Year Death Prediction Among Patients Receiving Hemodialysis, Karthikeyan K, Jennifer E Flythe, Patrick H Pun, Wolfgang C Winkelmayer, David Carlson

Faculty, Staff and Students Publications

Objectives: We evaluated the data requirement for modern AI tools to outperform simpler models in predicting short-term mortality in over 500 000 patients with hemodialysis-dependent kidney failure.

Materials and methods: We compared logistic regression, boosting, and transformers using increasingly complex feature sets (from last-visit data to full trajectories). Performance was measured using the area under the ROC curve (AUC-ROC) and the Precision-Recall curve (AUC-PR) across training data sizes ranging from 500 to 490 197 samples.

Results: Using features with temporal information is beneficial across all models. On the full dataset, Transformers (AUC-ROC = 0.8568) and boosting (AUC-ROC = 0.8598) perform …

Prioritising Follow-Up For People With Suspected Epilepsy Using A Digital Eeg Biomarker, Rohit Shankar, John Terry

Peninsula Medical School

Lengthy waits for follow-up testing are common for people with suspected epilepsy. This delays diagnosis, prolongs uncertainty and increases seizure risk. Initial EEGs are frequently inconclusive, yet follow-ups are often dictated by referral date, and there is no established method for risk-based prioritisation. Here, we tested whether an established digital EEG biomarker could help prioritise those most likely to have epilepsy for expedited follow-up EEG testing. We analysed 196 normal non-contributory (non-diagnostic) initial EEGs collected from six National Health Service (NHS) sites in England. From these recordings, we extracted eight previously validated computational features that quantify the likelihood that the …

Design And Implementation Of A Solar-Powered Autonomous Drain-Cleaning Robot With Iot And Vision-Based Debris Detection, Nik Nor Afiza Che Isa, Nor Zaihar Yahaya

Platform: A Journal of Engineering

Drain blockages caused by dried leaves and debris are a recurring issue in residential areas, particularly in tropical regions such as Malaysia leading to hygiene risks and increased manual maintenance effort. This paper presents the design and implementation of a solar-powered autonomous drain-cleaning robot for domestic applications. The system integrates a mobile robotic platform with a 4-DOF robotic arm, YOLOv8-based vision for real-time debris detection, and Internet of Things (IoT)-based remote monitoring. The robot is built on a Raspberry Pi 5 and incorporates VL53L0X time-of-flight (ToF) sensors, INA219 power sensors, NEO-6M GPS and a USB webcam. Detected debris triggers an …

Secure Machine Learning In Networking Systems, Wenwei Zhao

USF Tampa Graduate Theses and Dissertations

With the rapid integration of Machine Learning (ML) into networking systems, ensuring the security and trustworthiness of these intelligent frameworks has become a paramount concern. While ML offers unprecedented capabilities in spectrum management and collaborative learning, it also introduces novel vulnerabilities that can be exploited by sophisticated adversaries. This dissertation investigates and addresses critical security challenges across three key dimensions of ML-driven networking: adversarial spectrum sensing, the security of privacy-preserving unlearning processes, and efficient post-attack model recovery.

First, we address the threat of adversarial spectrum attacks in cognitive radio networks, where malicious nodes manipulate sensing reports to disrupt spectrum access. …

Iah-Net (Informative Air Quality And Heat Index Network): Drone-Assisted System For Real-Time Air Quality And Heat Index Monitoring, Brent Breo B. Magbanua

DLSU Senior High School Research Congress Conference Proceedings

Air pollution and rising temperatures threaten public health and safety, necessitating advanced monitoring solutions. This study developed a drone-assisted system for autonomous monitoring of air quality and heat index, ensuring real-time alerts even in the absence of human presence. By integrating the K-Nearest Neighbors (K-NN) machine learning algorithm, the system provides an innovative and cost-effective approach to identifying environmental risks and raising awareness. The system consists of a Drone system, ESP32, MQ-135 gas sensor, and DHT11 temperature and humidity sensor for data acquisition. Software development includes implementing the K-NN algorithm and calibrating sensors to enhance classification accuracy. The system categorizes …

Addressing The Problems Of Data Variations, Quality, And Scarcity In Training Deep Neural Networks, Jian Sun

Electronic Theses and Dissertations

The performance of deep neural networks (DNNs) is strongly influenced by the characteristics and quality of the underlying datasets. This Ph.D. dissertation addresses three pervasive data challenges-imbalance, quality degradation, and scarcity-that commonly hinder the effectiveness of DNNs in computer vision (CV) and natural language processing (NLP) applications.

Class imbalance remains one of the most frequent causes of degraded model generalization. While Focal Loss effectively mitigates inter-class imbalance by assigning higher weights to minority classes, it struggles with intra-class imbalance, particularly in video datasets where longer clips dominate feature representation. To address this, I implement and utilize …

Clinical Prediction Of Posttreatment Migraine Recurrence Using Biofeedback Data: A Machine Learning Framework For Enhanced Patient Stratification And Treatment Monitoring, Shibbir Ahmed Arif, Ferdib-Al-Islam, Mehidy Hasan Sium

School of Computing Faculty Scholarship and Creative Works

Migraine is a complex neurological disorder with significant implications for individual well-being and public health. Predicting migraine occurrences after treatment is crucial for evaluating therapeutic efficacy and enabling personalized care, yet remains largely underexplored. This study proposes a robust machine learning framework to predict posttreatment migraine headache occurrences using real-world headache log data collected from 133 patients undergoing biofeedback therapy. The methodology includes rigorous data preprocessing, outlier removal via the interquartile range (IQR) method, and class imbalance correction through the synthetic minority oversampling technique (SMOTE). A total of 10 classical and a hybrid ensemble machine learning models were developed and …

Artificial Intelligence In Medicine: A Definition Of Terms, Teray Johnson, Melvin Blanchard

Journal of Community Hospital Internal Medicine Perspectives

As artificial intelligence (AI) tools gain traction in clinical, operational, and administrative settings, healthcare professionals must develop a foundational understanding of key AI concepts to engage with these technologies responsibly and effectively. This perspective outlines essential AI terminology—such as machine learning, generative and agentic AI, large language models, artificial neural networks, and prompt engineering—paired with concrete clinical examples to illustrate their relevance in modern medical practice. By clarifying these terms and exploring their applications, this paper aims to equip healthcare leaders with the vocabulary and context necessary to evaluate, implement, and oversee AI systems within their organizations. Such literacy is …

The Developing Role Of Ai In Modern Engineering Research, Rianna Pais

The Cardinal Edge

No abstract provided.

Roadmap: Integrating Artificial Intelligence In Structural Health Monitoring Systems, Simon Laflamme, Erik Blasch, Flippo Ubertini, Zheng Liu, John Wertz, Christine Knott, Matthew Cherry, Eric Lindgren, Fu-Kuo Chang, Amrita Kumar, Jack Poole, Keith Worden, Austin Downey, Jie Wei, Patrick F. Musgrave, Adrian S. Wong, Guiseppe Quaranta, Marco Martino Rosso, Giuseppe Carlo Marano, Yu Chen, Et. Al.

Faculty Publications

Advances in computing and machine learning (ML) methods have led to a rapid rise in artificial intelligence (AI) research and applications in many fields. AI research benefitted from advances in computation hardware, collection and distribution of large data sets, and proliferation of software techniques. AI techniques include ML for provable results, deep learning for data exploration, reinforcement learning for control, and active learning for adaptive systems. Likewise, AI algorithms can handle large amounts of data, construct unknown representations, and provide a direct link between data and classification for decision making. These unmatched capabilities have been seen as a path to …

Empirical Evaluation Of A Cnn-Resnet-Rf Hybrid Model For Occupancy Rate Prediction In Passive Ultra-Low-Energy Buildings, Yiwen Liu, Yibing Xue, Chunlu Liu, Runyu Wang

Student Papers, Posters & Projects

Accurate occupancy information is critical for optimizing energy efficiency in buildings. Hybrid machine learning models have demonstrated great potential in previous studies; however, their application in passive ultra-low-energy buildings remains underexplored. This study conducts an empirical evaluation of real-time occupancy rate prediction using a CNN-ResNet-RF hybrid model based on multi-source environmental and behavioral data from a passive ultra-low-energy educational building. The model integrates Convolutional Neural Networks (CNN) for local feature extraction, Residual Networks (ResNet) to enhance deep feature representation, and Random Forests (RF) for ensemble-based generalization. Indoor CO₂ concentration exhibits the strongest linear correlation with occupancy rate (r = …

Predictive Analysis Of Greenhouse Gas Emissions From Electric Vehicle Charging In The United States, Mahyar Amirgholy, Faysal A. Chowdhoury, Chenyu Wang, S Nikhila Kanigiri

Faculty Articles

Electric vehicles (EVs) emit substantially fewer air pollutants than conventional internal combustion engine vehicles. However, the continuous increase in electricity demand from the power grid for EV charging, resulting from the growing adoption and total vehicle miles traveled, leads to higher greenhouse gas emissions from the power sector. This study presents a predictive analysis of energy sector greenhouse gas emissions from EV charging at the regional level across the United States under various projection scenarios of technology costs, fuel prices, demand growth, and electricity sector policies. The predictive modeling of greenhouse gas emissions from EV charging is performed using a …

Applications Of Artificial Intelligence In Nanotechnology, Shahad Eabd Alrida, Ola Obed, Elaf Taha, Thamer Abdullah, Mustafa Hathal, Viola Somogyi

Engineering and Technology Journal

Artificial intelligence (AI) is emerging as a prominent technological advancement. It is the act of replicating human intelligence for many purposes. In contrast to conventional methodologies, artificial intelligence (AI) is undergoing tremendous advancements. The present state of artificial intelligence (AI) technology enables them to effectively address numerous intricate difficulties with proficiency comparable to a human's. The significance of advancements in AI is particularly evident in machine learning, where the techniques and algorithms are effectively applied to address many problems, including those in nanotechnology. In contemporary nanotechnology, it is crucial to expedite the search for the most favorable synthesis parameters while …

Detection Of Arabic Sign Language By Machine Learning Techniques With Pca And Lda, Mosab Hassan, Atheer Sabri, Alaa Ali

Engineering and Technology Journal

People need a communication channel and a way to communicate with a person or group. Deaf people communicate with others through sign language. The remarkable and rapid development in image and video recognition systems has made researchers use this development to solve many problems, including sign language for the deaf, and reduce their suffering in communicating with ordinary people. This work aims to use and apply machine learning technology to build an automatic recognition system for Arabic Sign Language (ArSL). In this work, images of ArSL characters were recognized using four classification techniques (Naïve Bayes (NB), Decision Trees (DTs), and …

State-Of-The-Art Review Into Signal Processing And Artificial Intelligence-Based Approaches Applied In Gearbox Defect Diagnosis, Asaad Dubaish, Alaa Jaber

Engineering and Technology Journal

Various industrial applications, including rotating and reciprocating machinery, depend on gears. Therefore, a sudden breakdown of the gears could result in substantial financial losses. Due to this, extensive studies have focused on defect diagnosis. Both machinery maintenance decisions and preventive maintenance techniques have been aided by vibration analysis. An increased vibration is a warning sign that a machine is about to malfunction or break down. Observing and evaluating the machine's vibration pulses can identify the nature and extent of the issue and, as a result, predict when the machine will fail. The vibration signal may identify gearbox defects early on …

Enhancing Wind Tunnel Computational Simulations Of Finite Element Analysis Using Machine Learning-Based Algorithms, Luttfi Al-Haddad, Alaa Jaber, Latif Ibraheem, Sinan Al-Haddad, Naseem Ibrahim, Fawaz Abdulwahed

Engineering and Technology Journal

Wind tunnels are essential for examining aircraft model aerodynamics, accurately simulating real-world conditions, and enhancing design and performance evaluations. This study introduces a novel technique to improve the time and accuracy of stress distribution forecasts in wind tunnel simulations. This method combines Finite Element Analysis (FEA) with two regression models: Support Vector Machine (SVM) and k-Nearest Neighbors (kNN). The investigation begins with a thorough analysis of ANSYS fluent flow data, which reveals intricate fluid dynamics details within the wind tunnel. A comparative analysis of stress projections, supplemented by Root Mean Square Error (RMSE) metric, demonstrates the proposed methodology’s viability. High …

Future Water Requirements And Crop Productivity At Al-Najaf Governorate Under Different Climate Change Scenarios (2020–2080), Noor Sabah, Mustafa Al-Mukhtar, Khalid Shemal

Engineering and Technology Journal

This study aims to predict the effect of climate change on net irrigation water requirements (NIWR) and agricultural productivity from five common crops (wheat, barley, summer maize, and sorghum) in the Al-Najaf Governorate in Iraq. GFDL-ESM2M mode was used to predict the lower and upper temp and precipitation for two time periods (2020-2080) with 30 years for two periods (P1 and P2) under representative concentrations paths (RCP 2.5, RCP6, and RCP8.5). The CROPWAT model is used to determine NIWR, and the extreme learning model was used to estimate agricultural yields using previous crop yield production and weather data, supported vectors …

Improving Machine Learning Performance By Eliminating The Influence Of Unclean Data, Murtadha Ressan, Rehab Hassan

Engineering and Technology Journal

Regardless of the data source and type (text, digital, photo group, etc.), they are usually unclean data. The term (unclean) means that data contains some bugs and paradoxes that can strongly impact machine learning processes. The nature of the input data of the dataset is the most important reason for the success of the learning algorithm. More than one factor influences machine learning results in a specific task. The characteristics and the nature of the data are the main reasons for the algorithm's success. This paper generally examines data processing entered into an algorithm to learn machines. The paper explains …

The Effect Of Synthetic Minority Oversampling For Enhancing Brain Tumor Image Classification, Farah Fadhil, Zainab Sultani

Engineering and Technology Journal

Brain tumors are among the most serious neurological diseases, posing significant diagnostic challenges due to their diverse nature and complexity imbalance in medical imaging datasets. To address these challenges, machine learning (ML) has demonstrated high potential in brain tumor classification; nevertheless, its overall performance can suffer when minority classes are underrepresented. This study examines the impact of the Synthetic Minority Over-sampling Technique (SMOTE) on MRI brain tumor classification using handcrafted features, including Gray Level Co-occurence Matrix (GLCM), Histogram of Oriented Gradients (HOG), and their combination (HOG + GLCM), with three classifiers, namely, Logistic Regression (LR), Support Vector Machines (SVM), and …

Traditional Machine Learning Techniques For Explainable Ai In Lung And Colon Cancer Classification, Mahmood Amer, Zainab Sultani

Engineering and Technology Journal

Lung and colon cancers are two of the most common and deadly tumors around the world, creating significant public health concerns. Artificial intelligence (AI) and machine learning (ML) have heavily improved cancer research, particularly in early detection, histopathological analysis, and personalized therapy planning. However, despite their remarkable accuracy, ML models sometimes lack transparency, making explainability crucial in medical applications. Although various machine learning (ML)-based classifications for cancer models exist, their interpretation is not understood. The current research overcomes the diagnostic gap by developing a highly accurate system that uses XAI (Explainable Artificial Intelligence) methods to clarify its predictions. We used …

Using Artificial Neural Networks To Predict The Compressive Strength Of Cement And Sawdust Ash-Treated Lateritic Soil, James Ukpai, Ugochukwu Okonkwo

Engineering and Technology Journal

Sawdust industrial residue could be hazardous to the environment, but it becomes pozzolanic when incinerated. Thus, harnessing sawdust ash (SDA) and lateritic soil as road construction materials for low-cost roads is apt. However, modeling and prediction of the properties of soils treated with SDA have received very little attention. This study predicted the compressive strength of lateritic soil treated with cement and SDA using an Artificial Neural Network (ANN). The soil was found to belong to A-2-4(0) in the AASHTO rating and clayey sand (SC) in the Unified Soil Classification System. The soil minerals composition was conducted using an x-ray …

An Optimize Canny Algorithm With Traditional Machine Learning For Edge Detection Enhancement, Russel Lafta, Zainab Sultani

Engineering and Technology Journal

Edge detection still represents a major challenge in image processing and computer vision because of the complexity and variability of real-world images. The canny algorithm is powerful in detecting edges. However, it is sensitive to noise, and as a result, may produce weak edges. The use of machine learning algorithms has significantly improved the performance of edge detection techniques. In this paper, an improved Canny edge detection algorithm is proposed by replacing the Gaussian filter with a bilateral filter. Also, a new approach for estimating Canny algorithm thresholds has been developed using the Flower Pollination algorithm. Subsequently, the improved Canny …

Development Of A Framework For Identifying Asphalt Pavement Cracking Distresses Using Machine Learning, Dingxin Cheng

Mineta Transportation Institute

Asphalt pavement cracking is one of the most critical distresses affecting pavement performance and service life. When pavement deteriorates, it can lead to safety hazards, higher vehicle maintenance costs, and expensive repairs for cities and states—making early detection essential for everyone who relies on the roadway system. To address this challenge, the research team developed a prototype cracking identification system that integrates a customized machine learning model with computer vision algorithms. High-resolution images collected from drones or ground-based cameras are processed within the system to automatically detect and classify major cracking types. The core of the framework utilizes the You …