Digital Commons Network^™

Singleadv: Single-Class Target-Specific Attack Against Interpretable Deep Learning Systems, Eldor Abdukhamidov, Mohammed Abuhamad, George K. Thiruvathukal, Hyoungshick Kim, Tamer Abuhmed

Computer Science: Faculty Publications and Other Works

In this paper, we present a novel Single-class target-specific Adversarial attack called SingleADV. The goal of SingleADV is to generate a universal perturbation that deceives the target model into confusing a specific category of objects with a target category while ensuring highly relevant and accurate interpretations. The universal perturbation is stochastically and iteratively optimized by minimizing the adversarial loss that is designed to consider both the classifier and interpreter costs in targeted and non-targeted categories. In this optimization framework, ruled by the first- and second-moment estimations, the desired loss surface promotes high confidence and interpretation score of adversarial samples. By …

Intelligent Solutions For Retroactive Anomaly Detection And Resolution With Log File Systems, Derek G. Rogers, Chanvo Nguyen, Abhay Sharma

SMU Data Science Review

This paper explores the intricate challenges log files pose from data science and machine learning perspectives. Drawing inspiration from existing methods, LAnoBERT, PULL, LLMs, and the breadth of recent research, this paper aims to push the boundaries of machine learning for log file systems. Our study comprehensively examines the unique challenges presented in our problem setup, delineates the limitations of existing methods, and introduces innovative solutions. These contributions are organized to offer valuable insights, predictions, and actionable recommendations tailored for Microsoft's engineers working on log data analysis.

Leveraging Transformer Models For Genre Classification, Andreea C. Craus, Ben Berger, Yves Hughes, Hayley Horn

SMU Data Science Review

As the digital music landscape continues to expand, the need for effective methods to understand and contextualize the diverse genres of lyrical content becomes increasingly critical. This research focuses on the application of transformer models in the domain of music analysis, specifically in the task of lyric genre classification. By leveraging the advanced capabilities of transformer architectures, this project aims to capture intricate linguistic nuances within song lyrics, thereby enhancing the accuracy and efficiency of genre classification. The relevance of this project lies in its potential to contribute to the development of automated systems for music recommendation and genre-based playlist …

Investigating Bias In Mortgage-Rate Machine Learning Models, Will Kalikman

Computer Science Senior Theses

Banks and fintech lenders increasingly rely on computer-aided models in lending decisions. Traditional models were interpretable: decisions were based on observable factors, such as whether a borrower's credit score was above a threshold value, and explainable in terms of combinations of these factors. In contrast, modern machine learning models are opaque and non-interpretable. Their opaqueness and reliance on historical data that is the artifact of past racial discrimination means these new models risk embedding and exacerbating such discrimination, even if lenders do not intend to discriminate. We calibrate two random forest classifiers using publicly available HMDA loan data and publicly …

Automatic Measurement Of Dialogue Engagingness In Multilingual Settings, Amila Ferron

Dissertations and Theses

Expansive use of large language models (LLMs) as dialogue systems brings increased importance to the evaluation of the responses they generate. Although evaluation of qualities such as coherence and fluency are readily possible with well-established automatic metrics, engagingness is often measured with human evaluation -- a process that can be costly and slows the pace of development. Existing automatic metrics for engagingness have low to moderate correlation with human annotations, evaluate the response without the conversation history, are complicated to implement, or are designed for a specific dataset. Moreover, they have been tested exclusively on English conversations. Given that dialogue …

Detecting Drifts In Data Streams Using Kullback-Leibler (Kl) Divergence Measure For Data Engineering Applications, Jeomoan Francis Kurian, Mohamed Allali

Engineering Faculty Articles and Research

The exponential growth of data coupled with the widespread application of artificial intelligence(AI) presents organizations with challenges in upholding data accuracy, especially within data engineering functions. While the Extraction, Transformation, and Loading process addresses error-free data ingestion, validating the content within data streams remains a challenge. Prompt detection and remediation of data issues are crucial, especially in automated analytical environments driven by AI. To address these issues, this study focuses on detecting drifts in data distributions and divergence within data fields processed from different sample populations. Using a hypothetical banking scenario, we illustrate the impact of data drift on automated …

Math, Chatgpt, And You: The Problem With Mathematical Accuracy In Large Language Models, Alexandre M. Hamel

Computer Science Senior Theses

ChatGPT and other Large Language Models (LLMs) currently do a good job at generating novel text across many domains, but math remains a consistent issue when it comes to the accuracy of answers generated by these models. My research into various ways to manipulate the model have led me to the conclusion that a general closed form solution to help LLMs with math is both unrealistic and likely impossible. LLMs can be trained more successfully as you narrow the problem space, but consideration must be taken on the part of human user to recognize when an LLM is detrimental to …

Space Bounds For Estimating Minimum Norm Of Solutions In Underconstrained Systems, Jeffrey Jiang

Computer Science Senior Theses

In this work, we wish to investigate the following situation: suppose we are in an underconstrained linear system where observations are constant but predictors are streaming in. That is, the number of predictors—and therefore the dimensionality of our solution—is changing. How hard is it for a streaming algorithm to maintain the ”size” or norm of the solution if we are constrained in space? More informally, can we keep track of the norm of the solution as new data is streaming in without naively memorizing all data and computing the solution directly? We first show a lower bound that any streaming …

Open Source Supply Chain Security: A Cost-Benefit Analysis Of Achieving Various Security Thresholds In Build Environments, Carly Retterer

Computer Science Senior Theses

Open source software has become a cornerstone of modern software development, offering unparalleled opportunities for innovation and collaboration. However, its widespread adoption has also introduced a host of security vulnerabilities, particularly in the software supply chain. This paper provides a comprehensive cost-benefit analysis of achieving various security thresholds to harden the build environment, focusing on isolated, hermetic, reproducible, and bootstrappable builds. For each build type, we provide a clear definition and outline the steps required for implementation. We then evaluate the associated costs and benefits of each build, emphasizing their roles in strengthening the build environment and enhancing supply chain …

Data-Driven Computing Methods For Nonlinear Physics Systems With Geometric Constraints, Yunjin Tong

Computer Science Senior Theses

In a landscape where scientific discovery is increasingly driven by data, the integration of machine learning (ML) with traditional scientific methodologies has emerged as a transformative approach. This paper introduces a novel, data-driven framework that synergizes physics-based priors with advanced ML techniques to address the computational and practical limitations inherent in first-principle-based methods and brute-force machine learning methods. Our framework showcases four algorithms, each embedding a specific physics-based prior tailored to a particular class of nonlinear systems, including separable and nonseparable Hamiltonian systems, hyperbolic partial differential equations, and incompressible fluid dynamics. The intrinsic incorporation of physical laws preserves the system's …

Whisper: Proximity-Based Authentication For Securely Sharing Secrets, Charles A. Vogel

Computer Science Senior Theses

Cryptography offers a wide arsenal of encryption methods to enable secure communication between two
devices that have already exchanged a shared secret. Existing techniques for exchanging a shared secret,
however, are often vulnerable to man-in-the-middle attacks, require special hardware for out-of-band com-
munications, or require a pre-existing Internet connection. With the constantly increasing prevalence of
Internet of Things (IoT) devices sharing sensitive information via wireless networks, the need for a method
to establish secure communication is more pressing than ever.
With this context, we present Whisper, a novel technique that combines elements of digital commu-
nication theory, cryptography, and probability …

Memories Of Recipes In Twentieth-Century Irish Cookbooks, Gary Thompson

Dublin Gastronomy Symposium

This paper analyses and categorises the ways in which authors and their publishers have chosen to include the author’s culinary, food and personal memories within the texts of twenty twentieth century Irish Cookbooks. Cookbooks are subjects of culinary nostalgia with the reading of a recipe capable of triggering in the reader a memory of a meal enjoyed, a dish cooked in times past by a loved one, or recollections of the disgust felt for a food hated in childhood. Independent from the reader, the culinary memories of the author can be captured at the time of publication in the text …

Academic Search And Discovery Tools In The Age Of Ai And Large Language Models: An Overview Of The Space, Aaron Tay

2024 AI for Research Week

In the ever-evolving landscape of academic research, “AI tools” for literature search and synthesis are currently getting a lot of attention. These tools promise to ramp up productivity, enabling us to accomplish more in less time or absorb more knowledge without drowning in endless reading. With the sheer number of these systems increasing daily, it's natural to wonder: are they really worth our time and money? And if they are, how should we go about picking the right one from the multitude of options?

In this talk, I will share my views on how the space has developed over two …

Advancing Objective Mobile Device Use Measurement Inchildren Ages 6–11 Through Built-In Device Sensors: A Proof-Of-Concept Study, Olivia L. Finnegan, Robert Glenn Weaver Med, Phd, Hongpeng Yang, James W. White, Srihari Nelakuditi, Zifei Zhong, Rahul Ghosal Ph.D., Yan Tong, Aliye B. Cepni, Elizabeth L. Adams, Sarah Burkart Mph, Ph.D., Michael W. Beets Med, Mph, Phd, Bridget Armstrong Ph.D.

Faculty Publications

Mobile devices (e.g., tablets and smartphones) have been rapidly integrated into the lives of children and have impacted howchildren engage with digital media. The portability of these devices allows for sporadic, on-demand interaction, reducing theaccuracy of self-report estimates of mobile device use. Passive sensing applications objectively monitor time spent on a givendevice but are unable to identify who is using the device, a significant limitation in child screen time research. Behavioralbiometric authentication, using embedded mobile device sensors to continuously authenticate users, could be applied toaddress this limitation. This study examined the preliminary accuracy of machine learning models trained on iPad …

Ripl: Recursive Inference For Policy Learning, Kunal Jha, Jeremy R. Manning, Alberto Quattrini Li

Computer Science Senior Theses

Humans excel at understanding the thoughts and intentions of others (theory of mind) and leverage this ability to learn and adapt in social environments. However, replicating this capability in artificial agents remains a challenge. This paper explores the gap between fast, efficient learning often achieved by Reinforcement Learning (RL) algorithms and the interpretability and adaptability desired in agents interacting with humans. We propose a novel approach that integrates an inference network within existing RL frameworks. This allows agents to reason about the beliefs of others (nested reasoning) while learning optimal actions. Our method leverages approximate solutions to the I-POMDP framework, …

Elm And Lightgbm: A Hybrid Machine Learning Technique With Intelligent Iot To Predict The Cardiovascular Disease, Gorapalli Srinivasa Rao, G Muneeswari

Karbala International Journal of Modern Science

Cardiologists can more accurately classify a patient's condition by performing an accurate diagnostic and prognosis of cardiovascular disease (CVD). The clinical diagnosis, and therapies processes within the medical field have been substantially accelerated by ML-based approaches enabled by IoT-based systems. This structure is based on IoT-based system with enabled ML approach. This study investigates an approach known as ensemble categorization, which enhances the precision of weak algorithms by integrating multiple classifiers. For effective CVD classification, we utilized Ensemble learning machine (ELM) and Light GBM. The appropriate traits are chosen to speed up the categorization process using the Gorilla Troops Optimizer …

A Systems Theoretic View Of Speculative Realism, Martin Zwick

Complex Systems Faculty Publications and Presentations

Recent developments in Continental philosophy have included the emergence of a school of “speculative realism,” which rejects the human-centered orientation that has long dominated Continental thought. Proponents of speculative realism differ on several issues, but many agree on the need for an object-oriented ontology. Some speculative realists identify realism with materialism, while others accord equal reality to objects that are non-material, even fictional. Several thinkers retain a focus on difference, a well-established theme in Continental thought. This paper looks at speculative realism from the perspective of systems theory. Many of the tenets of speculative realism have long been features of …

Context Aware Music Recommendation And Playlist Generation, Elias Mann

SMU Journal of Undergraduate Research

There are many reasons people listen to music, and the type of music is largely determined by what the listener may be doing while they listen. For example, one may listen to one type of music while commuting, another while exercising, and yet another while relaxing. Without access to the physiological state of the user, current music recommendation methods rely on collaborative filtering - recommending music based on what other similar users listen to - and content based filtering - recommending songs based on their similarities to songs the user already prefers. With the rise in popularity of smart devices …

Classification Of Major Solar Flares From Extremely Imbalanced Multivariate Time Series Data Using Minimally Random Convolutional Kernel Transform, Kartik Saini, Khaznah Alshammari, Shah Muhammad Hamdi, Soukaina Filali Boubrahimi

Computer Science Faculty and Staff Publications

Solar flares are characterized by sudden bursts of electromagnetic radiation from the Sun’s surface, and are caused by the changes in magnetic field states in active solar regions. Earth and its surrounding space environment can suffer from various negative impacts caused by solar flares, ranging from electronic communication disruption to radiation exposure-based health risks to astronauts. In this paper, we address the solar flare prediction problem from magnetic field parameter-based multivariate time series (MVTS) data using multiple state-of-the-art machine learning classifiers that include MINImally RandOm Convolutional KErnel Transform (MiniRocket), Support Vector Machine (SVM), Canonical Interval Forest (CIF), Multiple Representations Sequence …

Databases And Privacy Compliance, Nick Scope

College of Computing and Digital Media Dissertations

Data privacy requirements are a complex and quickly evolving part of the data management domain. How long data must be retained, when data must be destroyed, and under what conditions data is processed is subject to rules from a variety of sources. There is a focus on data privacy and protection resulting in rules from a variety of sources including government requirements (e.g., United States Health Insurance Portability and Accountability Act and the European Union's General Data Protection Regulation).

Within a database, a single value within a row can be subject to multiple requirements on how long it must be …

Neighboring-Aware Hierarchical Clustering, Ali A. Amer, Muna Al-Razgan, Hassan I. Abdalla, Mahfoudh Al-Asaly, Taha Alfakih, Muneer Al-Hammadi

All Works

In this work, a simple yet robust neighboring-aware hierarchical-based clustering approach (NHC) is developed. NHC employs its dynamic technique to take into account the surroundings of each point when clustering, making it extremely competitive. NHC offers a straightforward design and reliable clustering. It comprises two key techniques, namely, neighboring- aware and filtering and merging. While the proposed neighboring-aware technique helps find the most coherent clusters, filtering and merging help reach the desired number of clusters during the clustering process. The NHC's performance, which includes all evaluation metrics and run time, has been thoroughly tested against nine clustering rivals using four …

A Deep Learning Framework For Blockage Mitigation In Mmwave Wireless, Ahmed Hazaa Almutairi

Dissertations and Theses

Millimeter-Wave (mmWave) communication is a key technology to enable next generation wireless systems. However, mmWave systems are highly susceptible to blockages, which can lead to a substantial decrease in signal strength at the receiver. Identifying blockages and mitigating them is thus a key challenge to achieve next generation wireless technology goals, such as enhanced mobile broadband (eMBB) and Ultra-Reliable and Low-Latency Communication (URLLC). This thesis proposes several deep learning (DL) frameworks for mmWave wireless blockage detection, mitigation, and duration prediction. First, we propose a DL framework to address the problem of identifying whether the mmWave wireless channel between two devices …

Unveiling Anomalies: A Survey On Xai-Based Anomaly Detection For Iot, Esin Eren, Feyza Yildirim Okay, Suat Özdemi̇r

Turkish Journal of Electrical Engineering and Computer Sciences

In recent years, the rapid growth of the Internet of Things (IoT) has raised concerns about the security and reliability of IoT systems. Anomaly detection is vital for recognizing potential risks and ensuring the optimal functionality of IoT networks. However, traditional anomaly detection methods often lack transparency and interpretability, hindering the understanding of their decisions. As a solution, Explainable Artificial Intelligence (XAI) techniques have emerged to provide human-understandable explanations for the decisions made by anomaly detection models. In this study, we present a comprehensive survey of XAI-based anomaly detection methods for IoT. We review and analyze various XAI techniques, including …

Text-To-Sql: A Methodical Review Of Challenges And Models, Ali Buğra Kanburoğlu, Faik Boray Tek

Turkish Journal of Electrical Engineering and Computer Sciences

This survey focuses on Text-to-SQL, automated translation of natural language queries into SQL queries. Initially, we describe the problem and its main challenges. Then, by following the PRISMA systematic review methodology, we survey the existing Text-to-SQL review papers in the literature. We apply the same method to extract proposed Text-to-SQL models and classify them with respect to used evaluation metrics and benchmarks. We highlight the accuracies achieved by various models on Text-to-SQL datasets and discuss execution-guided evaluation strategies. We present insights into model training times and implementations of different models. We also explore the availability of Text-to-SQL datasets in non-English …

Security Fusion Method Of Physical Fitness Training Data Based On The Internet Of Things, Bin Zhou

Turkish Journal of Electrical Engineering and Computer Sciences

Physical fitness training, an important way to improve physical fitness, is the basic guarantee for forming combat effectiveness. At present, the evaluation types of physical fitness training are mostly conducted manually. It has problems such as low efficiency, high consumption of human and material resources, and subjective factors affecting the evaluation results. ”Internet+” has greatly expanded the traditional network from the perspective of technological convergence and network coverage objects. It has expedited and promoted the rapid development of Internet of Things (IoT) technology and its applications. The IoT with many sensor nodes shows the characteristics of acquisition information redundancy, node …

Dpafy-Gcaps: Denoising Patch-And-Amplify Gabor Capsule Network For The Recognition Of Gastrointestinal Diseases, Henrietta Adjei Pokuaa, Adeboya Felix Adekoya, Benjamin Asubam Weyori, Owusu Nyarko-Boateng

Turkish Journal of Electrical Engineering and Computer Sciences

Deep learning (DL) models have performed tremendously well in image classification. This good performance can be attributed to the availability of massive data in most domains. However, some domains are known to have few datasets, especially the health sector. This makes it difficult to develop domain-specific high-performing DL algorithms for these fields. The field of health is critical and requires accurate detection of diseases. In the United States Gastrointestinal diseases are prevalent and affect 60 to 70 million people. Ulcerative colitis, polyps, and esophagitis are some gastrointestinal diseases. Colorectal polyps is the third most diagnosed malignancy in the world. This …

Stereo-Image-Based Ground-Line Prediction And Obstacle Detection, Emre Güngör, Ahmet Özmen

Turkish Journal of Electrical Engineering and Computer Sciences

In recent years, vision systems have become essential in the development of advanced driver assistance systems or autonomous vehicles. Although deep learning methods have been the center of focus in recent years to develop fast and reliable obstacle detection solutions, they face difficulties in complex and unknown environments where objects of varying types and shapes are present. In this study, a novel non-AI approach is presented for finding the ground-line and detecting the obstacles in roads using v-disparity data. The main motivation behind the study is that the ground-line estimation errors cause greater deviations at the output. Hence, a novel …

Deep Learning-Based Breast Cancer Diagnosis With Multiview Of Mammography Screening To Reduce False Positive Recall Rate, Meryem Altın Karagöz, Özkan Ufuk Nalbantoğlu, Derviş Karaboğa, Bahriye Akay, Alper Baştürk, Halil Ulutabanca, Serap Doğan, Damla Coşkun, Osman Demi̇r

Turkish Journal of Electrical Engineering and Computer Sciences

Breast cancer is the most prevalent and crucial cancer type that should be diagnosed early to reduce mortality. Therefore, mammography is essential for early diagnosis owing to high-resolution imaging and appropriate visualization. However, the major problem of mammography screening is the high false positive recall rate for breast cancer diagnosis. High false positive recall rates psychologically affect patients, leading to anxiety, depression, and stress. Moreover, false positive recalls increase costs and create an unnecessary expert workload. Thus, this study proposes a deep learning based breast cancer diagnosis model to reduce false positive and false negative rates. The proposed model has …

Signer-Independent Sign Language Recognition With Feature Disentanglement, İnci̇ Meli̇ha Baytaş, İpek Erdoğan

Turkish Journal of Electrical Engineering and Computer Sciences

Learning a robust and invariant representation of various unwanted factors in sign language recognition (SLR) applications is essential. One of the factors that might degrade the sign recognition performance is the lack of signer diversity in the training datasets, causing a dependence on the singer’s identity during representation learning. Consequently, capturing signer-specific features hinders the generalizability of SLR systems. This study proposes a feature disentanglement framework comprising a convolutional neural network (CNN) and a long short-term memory (LSTM) network based on adversarial training to learn a signer-independent sign language representation that might enhance the recognition of signs. We aim to …

Analysing An Imbalanced Stroke Prediction Dataset Using Machine Learning Techniques, Viswapriya Subramaniyam Elangovan, Rajeswari Devarajan, Osamah I. Khalaf, Mhd Saeed Sharif, Wael Elmedany

Karbala International Journal of Modern Science

A stroke is a medical condition characterized by the rupture of blood vessels within the brain which can lead to brain damage. various symptoms may be exhibited when the brain's supply of blood and essential nutrients is disrupted. To forecast the possibility of brain stroke occurring at an early stage using Machine Learning and Deep Learning is the main objective of this study. Timely detection of the various warning signs of a stroke can significantly reduce its severity. This paper performed a comprehensive analysis of features to enhance stroke prediction effectiveness. A reliable dataset for stroke prediction is taken from …