Artificial Intelligence and Robotics Commons^™

Closing The Interpretability Gap: Explainable Ml-Based Malware Detection For Defensive Cyberspace Operations, Tashi Stirewalt, Sean Hodgson, Puumaaya Tahiru, Assefaw Gebremedhin

Military Cyber Affairs

This paper presents an end-to-end, explainable malware triage pipeline designed for defense-oriented cyber operations. It combines high-performance static detection methods with analyst-centered interpretability. Utilizing the EMBER 2024 Windows PE subset, we train and evaluate four classifiers and select LightGBM as the production model based on its predictive performance, inference efficiency, and compatibility with exact tree-based attribution. The deployed system consists of four sequential components: PE feature extraction, malware probability scoring, dual explainability (using SHAP and LIME), and large language model (LLM) report generation, all integrated within a Flask web interface. On a temporal test set of 1,080,000 samples, LightGBM achieves …

Optimizing Gated Rnns, Joshua Paul Fechete

Honors Projects

Gated recurrent neural networks such as Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) help fix instability present in normal recurrent neural networks. This allows them to be used for various real-world tasks, and due to their architecture, they are uniquely qualified to handle variable sized input such as text. However, even before training can begin on a machine learning model, various hyperparameters must be chosen to decide how the model will be architectured. Choosing good hyperparameters is vital for creating a model that performs well but is not larger and more computationally expensive to run than it needs …

Understanding Bias And Fairness In Large Language Models: An Empirical Study, Joshua Johnson

Electrical Engineering and Computer Science Undergraduate Honors Theses

This thesis investigates demographic bias in large language models (LLMs) through the use of evaluating outcome disparities when utilized in decision making tasks as well as underlying associations that could contribute to furthering these disparities. Using profiles from the Adult dataset, we analyze how Gemini 2.0 Flash performs in an income prediction task using zero-shot and few-shot prompting methods. Our findings show that models exhibit measurable differences in demographic parity and false positive rates, with the use of few-shot prompting reducing these disparities. Alongside this line of testing, we tested associational bias in Qwen 2.5 using probability based association tests …

Hidden Layer Reshaping On Convolutional Neural Network, Alan Delgado

Open Access Theses & Dissertations

Artificial Intelligence (AI) technologies have become really popular in recent years. From ChatGPT to Tesla cars, many applications can benefit from these type of technologies. Automotive, healthcare, biomedical, cybersecurity, finances, and retail are some of the fields that take advantage of it. It has been seen that AI can solve complex problems, but there is still work to be done to optimize it. A deep learning neural network (DLNN) tries to simulate how a human brain operates. These DLNNs are made up of artificial neurons which are connected by weight that are modified when the network is trained. These networks …

Optiselect And Enshap: Integrating Machine Learning And Game Theory For Ischemic Stroke Prediction, Pritam Chakraborty, Anjan Bandyopadhyay, Sricheta Parul, Sujata Swain, Partha Sarathy Banerjee, Tapas Si, Hong Qin, Saurav Mallik

Computer Science Faculty Publications

Stroke analysis using game theory and machine learning techniques. The study investigates the use of the Shapley value in predictive ischemic brain stroke analysis. Initially, preference algorithms identify the most important features in various machine learning models, including logistic regression, K-nearest neighbor, decision tree, support vector machine (linear kernel), support vector machine ( RBF kernel), neural networks, etc. For each sample, the top 3, 4, and 5 features are evaluated and selected to evaluate their performance. The Shapley value method was used to rank the models using their best four features based on their predictive capabilities. As a result, better-performing …

Differentiating Opioid Use Disorder From Healthy Controls Via Ml Analysis Of Rs-Fmri Networks, Ahmed Temtam, Megan A. Witherow, Liangsuo Ma, M. Shibly Sadique, F. Gerard Moeller, C. Kenneth, Dianne Wright, Khan M. Iftekharuddin

Electrical & Computer Engineering Faculty Publications

Objectives/Goals: This work aims to identify functional brain networks that differentiate opioid use disorder (OUD) subjects from healthy controls (HC) using machine learning (ML) analysis of resting-state fMRI (rs-fMRI). We investigate the default mode network (DMN), salience network (SN), and executive control network (ECN), as well as demographic features. Methods/Study Population: This work uses high-resolution rs-fMRI data from a National Institute on Drug Abuse study (IRB #HM20023630) with 31 OUD and 45 HC subjects. We extract rs-fMRI blood oxygenation level-dependent (BOLD) features from the DMN, SN, and ECN. The Boruta ML algorithm identifies statistically significant features and brain activity mapping …

A Fast Framework For Generating Radioactive Mixture Spectra And Its Application To Remote High-Performance Mixture Identification, Chiman Kwan, Bulent Ayhan, Adam Stavola, Kazi Aminul Islam, Hongfang Zhang, Jiang Li

Electrical & Computer Engineering Faculty Publications

Remote detection of radioactive materials in mixtures using handheld or portal detectors remains a challenge because of factors such as low concentration, environmental interference, sensor noise, and other complications. This work introduces a fast framework for generating realistic mixture spectra. Moreover, we present mixture isotope identification using data generated by the fast framework. Researchers have examined a range of conventional and recent algorithms within the fields of machine learning and deep learning. An application to uranium enrichment-level prediction has been included. Extensive simulation experiments validated the efficacy of the proposed framework.

Land Target Detection Algorithm In Remote Sensing Images Based On Deep Learning, Wenyi Hu, Xiaomeng Jiang, Jiawei Tian, Shitong Ye, Shan Liu

Electrical & Computer Engineering Faculty Publications

Remote sensing technology plays a crucial role across various sectors, such as meteorological monitoring, city planning, and natural resource exploration. A critical aspect of remote sensing image analysis is land target detection, which involves identifying and classifying land-based objects within satellite or aerial imagery. However, despite advancements in both traditional detection methods and deep-learning-based approaches, detecting land targets remains challenging, especially when dealing with small and rotated objects that are difficult to distinguish. To address these challenges, this study introduces an enhanced model, YOLOv5s-CACSD, which builds upon the YOLOv5s framework. Our model integrates the channel attention (CA) mechanism, CARAFE, and …

A Generalized Machine Learning Model For Long-Term Coral Reef Monitoring In The Red Sea, Justin J. Gapper, Surendra Maharjan, Wenzhao Li, Erik Linstead, Surya Prakash Tiwari, Mohamed A. Qurban, Hesham El-Askary

Mathematics, Physics, and Computer Science Faculty Articles and Research

Coral reefs, despite covering less than 0.2 % of the ocean floor, harbor approximately 35 % of all known marine species, making their conservation critical. However, coral bleaching, exacerbated by climate change and phenomena such as El Niño, poses a significant threat to these ecosystems. This study focuses on the Red Sea, proposing a generalized machine learning approach to detect and monitor changes in coral reef cover over an 18-year period (2000–2018). Using Landsat 7 and 8 data, a Support Vector Machine (SVM) classifier was trained on depth-invariant indices (DII) derived from the Gulf of Aqaba and validated against ground …

A Deep Fuzzy Classifier Based On Feature Transform And Reconstruction, Rui Yin, Wei Lu, Jianhua Yang

Journal of System Simulation

Abstract: To obtain a classifier with good classification accuracy and interpretability, a deep fuzzy classifier based on feature transform and reconstruction (FR-DFC) is proposed. In FR-DFC, several fuzzy systems (FT_FS) for feature transform and a multi-prototype fuzzy classification system (MPRFD_FS) are stacked together to realize the classification process of the model, based on the hierarchically stacked thought originated from deep learning. Specifically, the stacked FT_FSs explore the hidden features in the data by transferring data from the original data space to the high-level feature space. MPRFD_FS, on the other hand, implements classification based on multiple prototypes that characterize the distribution …

Privacy Protection In Mobile Photography With Face Cloaking, Rithyka Heng

Computer Science and Computer Engineering Undergraduate Honors Theses

In a world of increasing connectivity, privacy is becoming ever-more difficult to maintain. People have little control over the capture of their image while in public and have even less control over the online sharing or posting of their image. This leaves many people vulnerable to being tracked or profiled via their image’s presence in other people’s photos. This thesis implements and evaluates an approach to privacy protection that involves the photographers protecting the privacy of bystanders. Because most photographs are now being taken by smartphones, a mobile application is decidedly the technology that would best achieve widespread adoption and …

Satellite Image Analysis And Sidewalk Classification Using Deep Learning Models, Subeksha Khanal

Master's Theses

Lack of sidewalk pavement can contribute to pedestrian fatalities and injuries in the USA. Although many researchers have conducted research on sidewalk detection, there are not many publicly available datasets that we would work on for sidewalk classification. In this study, I conducted classification tasks using pretrained CNN models including VGG16 and ResNet50. I extended these models by adding custom layers at the top of pretrained layers, employing various techniques to improve the classification accuracy.

The dataset comprises 4,731 images of sidewalk based on occlusion levels, including images where the sidewalk is visible from overhead and instances where sidewalk is …

Cardiogpt: An Ecg Interpretation Generation Model, Guohua Fu, Jianwei Zheng, Islam Abudayyeh, Chizobam Ani, Cyril Rakovski, Louis Ehwerhemuepha, Hongxia Lu, Yongjuan Guo, Shenglin Liu, Huimin Chu, Bing Yang

Mathematics, Physics, and Computer Science Faculty Articles and Research

Numerous supervised learning models aimed at classifying 12-lead electrocardiograms into different groups have shown impressive performance by utilizing deep learning algorithms. However, few studies are dedicated to applying the Generative Pre-trained Transformer (GPT) model in interpreting electrocardiogram (ECG) using natural language. Thus, we are pioneering the exploration of this uncharted territory by employing the CardioGPT model to tackle this challenge. We used a dataset of ECGs (standard 10s, 12-channel format) from adult patients, with 60 distinct rhythms or conduction abnormalities annotated by board-certified, actively practicing cardiologists. The ECGs were collected from The First Affiliated Hospital of Ningbo University and Shanghai …

Human-Centered Machine Learning With Interpretable Visual Knowledge Discovery, Lincoln Huber

All Master's Theses

This research advances interpretable machine learning (ML) by introducing hyperblocks (HBs) as a structured, rule-based approach for creating transparent and accurate models using meaningful numeric attributes directly interpretable to end users. Key techniques, including Parallel Hyperblock Creation, Interactive Hyperblock Creation, Level n Hyperblock Creation, and k-Nearest Neighbor Hyperblock, provide a framework that ensures domain experts can meaningfully engage with the model’s decision-making process through lossless visualizations using General Line Coordinates (GLC). Case studies with the Wisconsin Breast Cancer and MNIST datasets demonstrated HBs' effectiveness in handling high-risk and complex classification tasks, offering interpretable accuracy that traditional models struggle to achieve. …

Machine-Learning-Enabled Diagnostics With Improved Visualization Of Disease Lesions In Chest X-Ray Images, Md. Fashiar Rahman, Tzu-Liang (Bill) Tseng, Michael Pokojovy, Peter Mccaffrey, Eric Walser, Scott Moen, Alex Vo, Johnny C. Ho

Mathematics & Statistics Faculty Publications

The class activation map (CAM) represents the neural-network-derived region of interest, which can help clarify the mechanism of the convolutional neural network’s determination of any class of interest. In medical imaging, it can help medical practitioners diagnose diseases like COVID-19 or pneumonia by highlighting the suspicious regions in Computational Tomography (CT) or chest X-ray (CXR) film. Many contemporary deep learning techniques only focus on COVID-19 classification tasks using CXRs, while few attempt to make it explainable with a saliency map. To fill this research gap, we first propose a VGG-16-architecture-based deep learning approach in combination with image enhancement, segmentation-based region …

Enhanced Skin Cancer Diagnosis Through Grid Search Algorithm-Optimized Deep Learning Models For Skin Lesion Analysis, Rudresh Pillai, Neha Sharma, Sheifali Gupta, Deepali Gupta, Sapna Juneja, Saurav Malik, Hong Qin, Mohammed S. Alqahtani, Amel Ksibi

Computer Science Faculty Publications

Skin cancer is a widespread and perilous disease that necessitates prompt and precise detection for successful treatment. This research introduces a thorough method for identifying skin lesions by utilizing sophisticated deep learning (DL) techniques. The study utilizes three convolutional neural networks (CNNs)-CNN1, CNN2, and CNN3-each assigned to a distinct categorization job. Task 1 involves binary classification to determine whether skin lesions are present or absent. Task 2 involves distinguishing between benign and malignant lesions. Task 3 involves multiclass classification of skin lesion images to identify the precise type of skin lesion from a set of seven categories. The most optimal …

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 …

Skipresnet: Crop And Weed Recognition Based On The Improved Resnet, Wenyi Hu, Tian Chen, Chunjie Lan, Shan Liu, Lirong Yin

Electrical & Computer Engineering Faculty Publications

Weeds have a detrimental effect on crop yield. However, the prevailing chemical weed control methods cause pollution of the ecosystem and land. Therefore, it has become a trend to reduce dependence on herbicides; realize a sustainable, intelligent weed control method; and protect the land. In order to realize intelligent weeding, efficient and accurate crop and weed recognition is necessary. Convolutional neural networks (CNNs) are widely applied for weed and crop recognition due to their high speed and efficiency. In this paper, a multi-path input skip-residual network (SkipResNet) was put forward to upgrade the classification function of weeds and crops. It …

Scene Classification Of Remote Sensing Image Based On Multi-Path Reconfigurable Neural Network, Wenyi Hu, Chunjie Lan, Tian Chen, Shan Liu, Lirong Yin, Lei Wang

Electrical & Computer Engineering Faculty Publications

Land image recognition and classification and land environment detection are important research fields in remote sensing applications. Because of the diversity and complexity of different tasks of land environment recognition and classification, it is difficult for researchers to use a single model to achieve the best performance in scene classification of multiple remote sensing land images. Therefore, to determine which model is the best for the current recognition classification tasks, it is often necessary to select and experiment with many different models. However, finding the optimal model is accompanied by an increase in trial-and-error costs and is a waste of …

Classification Of Beef And Pork Images Based On Color Features And Pseudo Nearest Neighbor Rule, Ahmad Awaluddin Baiti, Muhammad Fachrie, Saucha Diwandari

Elinvo (Electronics, Informatics, and Vocational Education)

This research is motivated by the need for halal foods in Muslim society with the purpose of avoiding non-halal foods, such as pork, that are sold in the market. Although beef and pork basically have different characteristics, not all Muslims know the differences. Moreover, people nowadays sell beef mixed with pork to obtain more profits. Hence, this paper proposed the implementation of the Pseudo-Nearest Neighbor Rule (PNNR) in classifying images of beef and pork slices based on color features. Based on the image dataset that has been collected, the very significant difference that can be identified visually between beef and …

Towards Long-Term Fairness In Sequential Decision Making, Yaowei Hu

Graduate Theses and Dissertations

With the development of artificial intelligence, automated decision-making systems are increasingly integrated into various applications, such as hiring, loans, education, recommendation systems, and more. These machine learning algorithms are expected to facilitate faster, more accurate, and impartial decision-making compared to human judgments. Nevertheless, these expectations are not always met in practice due to biased training data, leading to discriminatory outcomes. In contemporary society, countering discrimination has become a consensus among people, leading the EU and the US to enact laws and regulations that prohibit discrimination based on factors such as gender, age, race, and religion. Consequently, addressing algorithmic discrimination has …

Sarcasm Detection In English And Arabic Tweets Using Transformer Models, Rishik Lad

Computer Science Senior Theses

This thesis describes our approach toward the detection of sarcasm and its various types in English and Arabic Tweets through methods in deep learning. There are five problems we attempted: (1) detection of sarcasm in English Tweets, (2) detection of sarcasm in Arabic Tweets, (3) determining the type of sarcastic speech subcategory for English Tweets, (4) determining which of two semantically equivalent English Tweets is sarcastic, and (5) determining which of two semantically equivalent Arabic Tweets is sarcastic. All tasks were framed as classification problems, and our contributions are threefold: (a) we developed an English binary classifier system with RoBERTa, …

Using Deep Neural Networks To Classify Astronomical Images, Andrew D. Macpherson

Honors Projects

As the quantity of astronomical data available continues to exceed the resources available for analysis, recent advances in artificial intelligence encourage the development of automated classification tools. This paper lays out a framework for constructing a deep neural network capable of classifying individual astronomical images by describing techniques to extract and label these objects from large images.

An Explainable Deep Learning Prediction Model For Severity Of Alzheimer's Disease From Brain Images, Godwin O. Ekuma

Graduate Theses/Dissertations

Deep Convolutional Neural Networks (CNNs) have become the go-to method for medical imaging classification on various imaging modalities for binary and multiclass problems. Deep CNNs extract spatial features from image data hierarchically, with deeper layers learning more relevant features for the classification application. The effectiveness of deep learning models are hampered by limited data sets, skewed class distributions, and the undesirable "black box" of neural networks, which decreases their understandability and usability in precision medicine applications. This thesis addresses the challenge of building an explainable deep learning model for a clinical application: predicting the severity of Alzheimer's disease (AD). AD …

Prediction Of Sumoylation Sites In Proteins From Language Model Representations, Evgenii Sidorov

Dissertations, Master's Theses and Master's Reports

Sumoylation is an essential post-translational modification intimately involved in a diverse range of eukaryotic cellular mechanisms and plays a significant role in DNA repair. Some researchers hypothesize that a high level of SUMOylation events in cancer cells improves cells' chances for survival under stress conditions by regulating tumor-related proteins.

This study belongs to a booming field of harnessing computational power to the domain of life. Prediction of protein structure, its molecular function, and the design of new drugs are just a few examples of the applications within this exciting area of research. By leveraging computational power, researchers can analyze vast …

Multi-Domain Adaptation For Image Classification, Depth Estimation, And Semantic Segmentation, Yu Zhang

Theses and Dissertations--Computer Science

The appearance of scenes may change for many reasons, including the viewpoint, the time of day, the weather, and the seasons. Traditionally, deep neural networks are trained and evaluated using images from the same scene and domain to avoid the domain gap. Recent advances in domain adaptation have led to a new type of method that bridges such domain gaps and learns from multiple domains.

This dissertation proposes methods for multi-domain adaptation for various computer vision tasks, including image classification, depth estimation, and semantic segmentation. The first work focuses on semi-supervised domain adaptation. I address this semi-supervised setting and propose …

Machine-Learning-Based Vulnerability Detection And Classification In Internet Of Things Device Security, Sarah Bin Hulayyil, Shancang Li, Li Da Xu

Information Technology & Decision Sciences Faculty Publications

Detecting cyber security vulnerabilities in the Internet of Things (IoT) devices before they are exploited is increasingly challenging and is one of the key technologies to protect IoT devices from cyber attacks. This work conducts a comprehensive survey to investigate the methods and tools used in vulnerability detection in IoT environments utilizing machine learning techniques on various datasets, i.e., IoT23. During this study, the common potential vulnerabilities of IoT architectures are analyzed on each layer and the machine learning workflow is described for detecting IoT vulnerabilities. A vulnerability detection and mitigation framework was proposed for machine learning-based vulnerability detection in …

Deep-Learning-Based Classification Of Digitally Modulated Signals Using Capsule Networks And Cyclic Cumulants, John A. Snoap, Dimitrie C. Popescu, James A. Latshaw, Chad M. Spooner

Electrical & Computer Engineering Faculty Publications

This paper presents a novel deep-learning (DL)-based approach for classifying digitally modulated signals, which involves the use of capsule networks (CAPs) together with the cyclic cumulant (CC) features of the signals. These were blindly estimated using cyclostationary signal processing (CSP) and were then input into the CAP for training and classification. The classification performance and the generalization abilities of the proposed approach were tested using two distinct datasets that contained the same types of digitally modulated signals, but had distinct generation parameters. The results showed that the classification of digitally modulated signals using CAPs and CCs proposed in the paper …

Tutorial: Neuro-Symbolic Ai For Mental Healthcare, Kaushik Roy, Usha Lokala, Manas Gaur, Amit Sheth

Publications

Artificial Intelligence (AI) systems for mental healthcare (MHCare) have been ever-growing after realizing the importance of early interventions for patients with chronic mental health (MH) conditions. Social media (SocMedia) emerged as the go-to platform for supporting patients seeking MHCare. The creation of peer-support groups without social stigma has resulted in patients transitioning from clinical settings to SocMedia supported interactions for quick help. Researchers started exploring SocMedia content in search of cues that showcase correlation or causation between different MH conditions to design better interventional strategies. User-level Classification-based AI systems were designed to leverage diverse SocMedia data from various MH conditions, …

Eeg Signals Classification Using Lstm-Based Models And Majority Logic, James A. Orgeron

College of Graduate Studies: Theses & Dissertations

The study of elecroencephalograms (EEGs) has gained enormous interest in the last decade with the increase of computational power and availability of EEG signals collected from various human activities or produced during medical tests. The applicability of analyzing EEG signals ranges from helping impaired people communicate or move (using appropriate medical equipment) to understanding people's feelings and detecting diseases.

We proposed new methodology and models for analyzing and classifying EEG signals collected from individuals observing visual stimuli. Our models rely on powerful Long-Short Term Memory (LSTM) Neural Network models, which are currently the state of the art models for performing …